Learning dynamic Bayesian networks with mixed variables
DEFF Research Database (Denmark)
Bøttcher, Susanne Gammelgaard
This paper considers dynamic Bayesian networks for discrete and continuous variables. We only treat the case, where the distribution of the variables is conditional Gaussian. We show how to learn the parameters and structure of a dynamic Bayesian network and also how the Markov order can be learned...
Neuronal integration of dynamic sources: Bayesian learning and Bayesian inference.
Siegelmann, Hava T; Holzman, Lars E
2010-09-01
One of the brain's most basic functions is integrating sensory data from diverse sources. This ability causes us to question whether the neural system is computationally capable of intelligently integrating data, not only when sources have known, fixed relative dependencies but also when it must determine such relative weightings based on dynamic conditions, and then use these learned weightings to accurately infer information about the world. We suggest that the brain is, in fact, fully capable of computing this parallel task in a single network and describe a neural inspired circuit with this property. Our implementation suggests the possibility that evidence learning requires a more complex organization of the network than was previously assumed, where neurons have different specialties, whose emergence brings the desired adaptivity seen in human online inference.
Nonlinear Bayesian filtering and learning: a neuronal dynamics for perception.
Kutschireiter, Anna; Surace, Simone Carlo; Sprekeler, Henning; Pfister, Jean-Pascal
2017-08-18
The robust estimation of dynamical hidden features, such as the position of prey, based on sensory inputs is one of the hallmarks of perception. This dynamical estimation can be rigorously formulated by nonlinear Bayesian filtering theory. Recent experimental and behavioral studies have shown that animals' performance in many tasks is consistent with such a Bayesian statistical interpretation. However, it is presently unclear how a nonlinear Bayesian filter can be efficiently implemented in a network of neurons that satisfies some minimum constraints of biological plausibility. Here, we propose the Neural Particle Filter (NPF), a sampling-based nonlinear Bayesian filter, which does not rely on importance weights. We show that this filter can be interpreted as the neuronal dynamics of a recurrently connected rate-based neural network receiving feed-forward input from sensory neurons. Further, it captures properties of temporal and multi-sensory integration that are crucial for perception, and it allows for online parameter learning with a maximum likelihood approach. The NPF holds the promise to avoid the 'curse of dimensionality', and we demonstrate numerically its capability to outperform weighted particle filters in higher dimensions and when the number of particles is limited.
Mocapy++ - a toolkit for inference and learning in dynamic Bayesian networks
DEFF Research Database (Denmark)
Paluszewski, Martin; Hamelryck, Thomas Wim
2010-01-01
Background Mocapy++ is a toolkit for parameter learning and inference in dynamic Bayesian networks (DBNs). It supports a wide range of DBN architectures and probability distributions, including distributions from directional statistics (the statistics of angles, directions and orientations...
Yu, Bin; Xu, Jia-Meng; Li, Shan; Chen, Cheng; Chen, Rui-Xin; Wang, Lei; Zhang, Yan; Wang, Ming-Hui
2017-10-06
Gene regulatory networks (GRNs) research reveals complex life phenomena from the perspective of gene interaction, which is an important research field in systems biology. Traditional Bayesian networks have a high computational complexity, and the network structure scoring model has a single feature. Information-based approaches cannot identify the direction of regulation. In order to make up for the shortcomings of the above methods, this paper presents a novel hybrid learning method (DBNCS) based on dynamic Bayesian network (DBN) to construct the multiple time-delayed GRNs for the first time, combining the comprehensive score (CS) with the DBN model. DBNCS algorithm first uses CMI2NI (conditional mutual inclusive information-based network inference) algorithm for network structure profiles learning, namely the construction of search space. Then the redundant regulations are removed by using the recursive optimization algorithm (RO), thereby reduce the false positive rate. Secondly, the network structure profiles are decomposed into a set of cliques without loss, which can significantly reduce the computational complexity. Finally, DBN model is used to identify the direction of gene regulation within the cliques and search for the optimal network structure. The performance of DBNCS algorithm is evaluated by the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in Escherichia coli , and compared with other state-of-the-art methods. The experimental results show the rationality of the algorithm design and the outstanding performance of the GRNs.
Mocapy++ - A toolkit for inference and learning in dynamic Bayesian networks
Directory of Open Access Journals (Sweden)
Hamelryck Thomas
2010-03-01
Full Text Available Abstract Background Mocapy++ is a toolkit for parameter learning and inference in dynamic Bayesian networks (DBNs. It supports a wide range of DBN architectures and probability distributions, including distributions from directional statistics (the statistics of angles, directions and orientations. Results The program package is freely available under the GNU General Public Licence (GPL from SourceForge http://sourceforge.net/projects/mocapy. The package contains the source for building the Mocapy++ library, several usage examples and the user manual. Conclusions Mocapy++ is especially suitable for constructing probabilistic models of biomolecular structure, due to its support for directional statistics. In particular, it supports the Kent distribution on the sphere and the bivariate von Mises distribution on the torus. These distributions have proven useful to formulate probabilistic models of protein and RNA structure in atomic detail.
Dang, Shilpa; Chaudhury, Santanu; Lall, Brejesh; Roy, Prasun K
2018-05-01
Effective connectivity (EC) is the methodology for determining functional-integration among the functionally active segregated regions of the brain. By definition EC is "the causal influence exerted by one neuronal group on another" which is constrained by anatomical connectivity (AC) (axonal connections). AC is necessary for EC but does not fully determine it, because synaptic communication occurs dynamically in a context-dependent fashion. Although there is a vast emerging evidence of structure-function relationship using multimodal imaging studies, till date only a few studies have done joint modeling of the two modalities: functional MRI (fMRI) and diffusion tensor imaging (DTI). We aim to propose a unified probabilistic framework that combines information from both sources to learn EC using dynamic Bayesian networks (DBNs). DBNs are probabilistic graphical temporal models that learn EC in an exploratory fashion. Specifically, we propose a novel anatomically informed (AI) score that evaluates fitness of a given connectivity structure to both DTI and fMRI data simultaneously. The AI score is employed in structure learning of DBN given the data. Experiments with synthetic-data demonstrate the face validity of structure learning with our AI score over anatomically uninformed counterpart. Moreover, real-data results are cross-validated by performing classification-experiments. EC inferred on real fMRI-DTI datasets is found to be consistent with previous literature and show promising results in light of the AC present as compared to other classically used techniques such as Granger-causality. Multimodal analyses provide a more reliable basis for differentiating brain under abnormal/diseased conditions than the single modality analysis.
Bayesian dynamic mediation analysis.
Huang, Jing; Yuan, Ying
2017-12-01
Most existing methods for mediation analysis assume that mediation is a stationary, time-invariant process, which overlooks the inherently dynamic nature of many human psychological processes and behavioral activities. In this article, we consider mediation as a dynamic process that continuously changes over time. We propose Bayesian multilevel time-varying coefficient models to describe and estimate such dynamic mediation effects. By taking the nonparametric penalized spline approach, the proposed method is flexible and able to accommodate any shape of the relationship between time and mediation effects. Simulation studies show that the proposed method works well and faithfully reflects the true nature of the mediation process. By modeling mediation effect nonparametrically as a continuous function of time, our method provides a valuable tool to help researchers obtain a more complete understanding of the dynamic nature of the mediation process underlying psychological and behavioral phenomena. We also briefly discuss an alternative approach of using dynamic autoregressive mediation model to estimate the dynamic mediation effect. The computer code is provided to implement the proposed Bayesian dynamic mediation analysis. (PsycINFO Database Record (c) 2017 APA, all rights reserved).
Learning Bayesian networks for discrete data
Liang, Faming
2009-02-01
Bayesian networks have received much attention in the recent literature. In this article, we propose an approach to learn Bayesian networks using the stochastic approximation Monte Carlo (SAMC) algorithm. Our approach has two nice features. Firstly, it possesses the self-adjusting mechanism and thus avoids essentially the local-trap problem suffered by conventional MCMC simulation-based approaches in learning Bayesian networks. Secondly, it falls into the class of dynamic importance sampling algorithms; the network features can be inferred by dynamically weighted averaging the samples generated in the learning process, and the resulting estimates can have much lower variation than the single model-based estimates. The numerical results indicate that our approach can mix much faster over the space of Bayesian networks than the conventional MCMC simulation-based approaches. © 2008 Elsevier B.V. All rights reserved.
Motion Learning Based on Bayesian Program Learning
Directory of Open Access Journals (Sweden)
Cheng Meng-Zhen
2017-01-01
Full Text Available The concept of virtual human has been highly anticipated since the 1980s. By using computer technology, Human motion simulation could generate authentic visual effect, which could cheat human eyes visually. Bayesian Program Learning train one or few motion data, generate new motion data by decomposing and combining. And the generated motion will be more realistic and natural than the traditional one.In this paper, Motion learning based on Bayesian program learning allows us to quickly generate new motion data, reduce workload, improve work efficiency, reduce the cost of motion capture, and improve the reusability of data.
Learning Bayesian networks for discrete data
Liang, Faming; Zhang, Jian
2009-01-01
Bayesian networks have received much attention in the recent literature. In this article, we propose an approach to learn Bayesian networks using the stochastic approximation Monte Carlo (SAMC) algorithm. Our approach has two nice features. Firstly
Dang, Shilpa; Chaudhury, Santanu; Lall, Brejesh; Roy, Prasun Kumar
2017-06-15
Determination of effective connectivity (EC) among brain regions using fMRI is helpful in understanding the underlying neural mechanisms. Dynamic Bayesian Networks (DBNs) are an appropriate class of probabilistic graphical temporal-models that have been used in past to model EC from fMRI, specifically order-one. High-order DBNs (HO-DBNs) have still not been explored for fMRI data. A fundamental problem faced in the structure-learning of HO-DBN is high computational-burden and low accuracy by the existing heuristic search techniques used for EC detection from fMRI. In this paper, we propose using dynamic programming (DP) principle along with integration of properties of scoring-function in a way to reduce search space for structure-learning of HO-DBNs and finally, for identifying EC from fMRI which has not been done yet to the best of our knowledge. The proposed exact search-&-score learning approach HO-DBN-DP is an extension of the technique which was originally devised for learning a BN's structure from static data (Singh and Moore, 2005). The effectiveness in structure-learning is shown on synthetic fMRI dataset. The algorithm reaches globally-optimal solution in appreciably reduced time-complexity than the static counterpart due to integration of properties. The proof of optimality is provided. The results demonstrate that HO-DBN-DP is comparably more accurate and faster than currently used structure-learning algorithms used for identifying EC from fMRI. The real data EC from HO-DBN-DP shows consistency with previous literature than the classical Granger Causality method. Hence, the DP algorithm can be employed for reliable EC estimates from experimental fMRI data. Copyright © 2017 Elsevier B.V. All rights reserved.
BELM: Bayesian extreme learning machine.
Soria-Olivas, Emilio; Gómez-Sanchis, Juan; Martín, José D; Vila-Francés, Joan; Martínez, Marcelino; Magdalena, José R; Serrano, Antonio J
2011-03-01
The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap; and presents high generalization capabilities. Bayesian ELM is benchmarked against classical ELM in several artificial and real datasets that are widely used for the evaluation of machine learning algorithms. Achieved results show that the proposed approach produces a competitive accuracy with some additional advantages, namely, automatic production of CIs, reduction of probability of model overfitting, and use of a priori knowledge.
Sparse Bayesian Learning for Nonstationary Data Sources
Fujimaki, Ryohei; Yairi, Takehisa; Machida, Kazuo
This paper proposes an online Sparse Bayesian Learning (SBL) algorithm for modeling nonstationary data sources. Although most learning algorithms implicitly assume that a data source does not change over time (stationary), one in the real world usually does due to such various factors as dynamically changing environments, device degradation, sudden failures, etc (nonstationary). The proposed algorithm can be made useable for stationary online SBL by setting time decay parameters to zero, and as such it can be interpreted as a single unified framework for online SBL for use with stationary and nonstationary data sources. Tests both on four types of benchmark problems and on actual stock price data have shown it to perform well.
Hierarchical Bayesian Models of Subtask Learning
Anglim, Jeromy; Wynton, Sarah K. A.
2015-01-01
The current study used Bayesian hierarchical methods to challenge and extend previous work on subtask learning consistency. A general model of individual-level subtask learning was proposed focusing on power and exponential functions with constraints to test for inconsistency. To study subtask learning, we developed a novel computer-based booking…
Bayesian NL interpretation and learning
Zeevat, H.
2011-01-01
Everyday natural language communication is normally successful, even though contemporary computational linguistics has shown that NL is characterised by very high degree of ambiguity and the results of stochastic methods are not good enough to explain the high success rate. Bayesian natural language
Deep Learning and Bayesian Methods
Directory of Open Access Journals (Sweden)
Prosper Harrison B.
2017-01-01
Full Text Available A revolution is underway in which deep neural networks are routinely used to solve diffcult problems such as face recognition and natural language understanding. Particle physicists have taken notice and have started to deploy these methods, achieving results that suggest a potentially significant shift in how data might be analyzed in the not too distant future. We discuss a few recent developments in the application of deep neural networks and then indulge in speculation about how such methods might be used to automate certain aspects of data analysis in particle physics. Next, the connection to Bayesian methods is discussed and the paper ends with thoughts on a significant practical issue, namely, how, from a Bayesian perspective, one might optimize the construction of deep neural networks.
Multisnapshot Sparse Bayesian Learning for DOA
DEFF Research Database (Denmark)
Gerstoft, Peter; Mecklenbrauker, Christoph F.; Xenaki, Angeliki
2016-01-01
The directions of arrival (DOA) of plane waves are estimated from multisnapshot sensor array data using sparse Bayesian learning (SBL). The prior for the source amplitudes is assumed independent zero-mean complex Gaussian distributed with hyperparameters, the unknown variances (i.e., the source...
Machine learning a Bayesian and optimization perspective
Theodoridis, Sergios
2015-01-01
This tutorial text gives a unifying perspective on machine learning by covering both probabilistic and deterministic approaches, which rely on optimization techniques, as well as Bayesian inference, which is based on a hierarchy of probabilistic models. The book presents the major machine learning methods as they have been developed in different disciplines, such as statistics, statistical and adaptive signal processing and computer science. Focusing on the physical reasoning behind the mathematics, all the various methods and techniques are explained in depth, supported by examples and problems, giving an invaluable resource to the student and researcher for understanding and applying machine learning concepts. The book builds carefully from the basic classical methods to the most recent trends, with chapters written to be as self-contained as possible, making the text suitable for different courses: pattern recognition, statistical/adaptive signal processing, statistical/Bayesian learning, as well as shor...
Bayesian Inference and Online Learning in Poisson Neuronal Networks.
Huang, Yanping; Rao, Rajesh P N
2016-08-01
Motivated by the growing evidence for Bayesian computation in the brain, we show how a two-layer recurrent network of Poisson neurons can perform both approximate Bayesian inference and learning for any hidden Markov model. The lower-layer sensory neurons receive noisy measurements of hidden world states. The higher-layer neurons infer a posterior distribution over world states via Bayesian inference from inputs generated by sensory neurons. We demonstrate how such a neuronal network with synaptic plasticity can implement a form of Bayesian inference similar to Monte Carlo methods such as particle filtering. Each spike in a higher-layer neuron represents a sample of a particular hidden world state. The spiking activity across the neural population approximates the posterior distribution over hidden states. In this model, variability in spiking is regarded not as a nuisance but as an integral feature that provides the variability necessary for sampling during inference. We demonstrate how the network can learn the likelihood model, as well as the transition probabilities underlying the dynamics, using a Hebbian learning rule. We present results illustrating the ability of the network to perform inference and learning for arbitrary hidden Markov models.
Bayesian Inference of High-Dimensional Dynamical Ocean Models
Lin, J.; Lermusiaux, P. F. J.; Lolla, S. V. T.; Gupta, A.; Haley, P. J., Jr.
2015-12-01
This presentation addresses a holistic set of challenges in high-dimension ocean Bayesian nonlinear estimation: i) predict the probability distribution functions (pdfs) of large nonlinear dynamical systems using stochastic partial differential equations (PDEs); ii) assimilate data using Bayes' law with these pdfs; iii) predict the future data that optimally reduce uncertainties; and (iv) rank the known and learn the new model formulations themselves. Overall, we allow the joint inference of the state, equations, geometry, boundary conditions and initial conditions of dynamical models. Examples are provided for time-dependent fluid and ocean flows, including cavity, double-gyre and Strait flows with jets and eddies. The Bayesian model inference, based on limited observations, is illustrated first by the estimation of obstacle shapes and positions in fluid flows. Next, the Bayesian inference of biogeochemical reaction equations and of their states and parameters is presented, illustrating how PDE-based machine learning can rigorously guide the selection and discovery of complex ecosystem models. Finally, the inference of multiscale bottom gravity current dynamics is illustrated, motivated in part by classic overflows and dense water formation sites and their relevance to climate monitoring and dynamics. This is joint work with our MSEAS group at MIT.
Learning Bayesian Dependence Model for Student Modelling
Directory of Open Access Journals (Sweden)
Adina COCU
2008-12-01
Full Text Available Learning a Bayesian network from a numeric set of data is a challenging task because of dual nature of learning process: initial need to learn network structure, and then to find out the distribution probability tables. In this paper, we propose a machine-learning algorithm based on hill climbing search combined with Tabu list. The aim of learning process is to discover the best network that represents dependences between nodes. Another issue in machine learning procedure is handling numeric attributes. In order to do that, we must perform an attribute discretization pre-processes. This discretization operation can influence the results of learning network structure. Therefore, we make a comparative study to find out the most suitable combination between discretization method and learning algorithm, for a specific data set.
Discriminative Bayesian Dictionary Learning for Classification.
Akhtar, Naveed; Shafait, Faisal; Mian, Ajmal
2016-12-01
We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data. The proposed approach infers probability distributions over the atoms of a discriminative dictionary using a finite approximation of Beta Process. It also computes sets of Bernoulli distributions that associate class labels to the learned dictionary atoms. This association signifies the selection probabilities of the dictionary atoms in the expansion of class-specific data. Furthermore, the non-parametric character of the proposed approach allows it to infer the correct size of the dictionary. We exploit the aforementioned Bernoulli distributions in separately learning a linear classifier. The classifier uses the same hierarchical Bayesian model as the dictionary, which we present along the analytical inference solution for Gibbs sampling. For classification, a test instance is first sparsely encoded over the learned dictionary and the codes are fed to the classifier. We performed experiments for face and action recognition; and object and scene-category classification using five public datasets and compared the results with state-of-the-art discriminative sparse representation approaches. Experiments show that the proposed Bayesian approach consistently outperforms the existing approaches.
Evolution in Mind: Evolutionary Dynamics, Cognitive Processes, and Bayesian Inference.
Suchow, Jordan W; Bourgin, David D; Griffiths, Thomas L
2017-07-01
Evolutionary theory describes the dynamics of population change in settings affected by reproduction, selection, mutation, and drift. In the context of human cognition, evolutionary theory is most often invoked to explain the origins of capacities such as language, metacognition, and spatial reasoning, framing them as functional adaptations to an ancestral environment. However, evolutionary theory is useful for understanding the mind in a second way: as a mathematical framework for describing evolving populations of thoughts, ideas, and memories within a single mind. In fact, deep correspondences exist between the mathematics of evolution and of learning, with perhaps the deepest being an equivalence between certain evolutionary dynamics and Bayesian inference. This equivalence permits reinterpretation of evolutionary processes as algorithms for Bayesian inference and has relevance for understanding diverse cognitive capacities, including memory and creativity. Copyright © 2017 Elsevier Ltd. All rights reserved.
Characteristic imsets for learning Bayesian network structure
Czech Academy of Sciences Publication Activity Database
Hemmecke, R.; Lindner, S.; Studený, Milan
2012-01-01
Roč. 53, č. 9 (2012), s. 1336-1349 ISSN 0888-613X R&D Projects: GA MŠk(CZ) 1M0572; GA ČR GA201/08/0539 Institutional support: RVO:67985556 Keywords : learning Bayesian network structure * essential graph * standard imset * characteristic imset * LP relaxation of a polytope Subject RIV: BA - General Mathematics Impact factor: 1.729, year: 2012 http://library.utia.cas.cz/separaty/2012/MTR/studeny-0382596.pdf
Bayesian network learning for natural hazard assessments
Vogel, Kristin
2016-04-01
Even though quite different in occurrence and consequences, from a modelling perspective many natural hazards share similar properties and challenges. Their complex nature as well as lacking knowledge about their driving forces and potential effects make their analysis demanding. On top of the uncertainty about the modelling framework, inaccurate or incomplete event observations and the intrinsic randomness of the natural phenomenon add up to different interacting layers of uncertainty, which require a careful handling. Thus, for reliable natural hazard assessments it is crucial not only to capture and quantify involved uncertainties, but also to express and communicate uncertainties in an intuitive way. Decision-makers, who often find it difficult to deal with uncertainties, might otherwise return to familiar (mostly deterministic) proceedings. In the scope of the DFG research training group „NatRiskChange" we apply the probabilistic framework of Bayesian networks for diverse natural hazard and vulnerability studies. The great potential of Bayesian networks was already shown in previous natural hazard assessments. Treating each model component as random variable, Bayesian networks aim at capturing the joint distribution of all considered variables. Hence, each conditional distribution of interest (e.g. the effect of precautionary measures on damage reduction) can be inferred. The (in-)dependencies between the considered variables can be learned purely data driven or be given by experts. Even a combination of both is possible. By translating the (in-)dependences into a graph structure, Bayesian networks provide direct insights into the workings of the system and allow to learn about the underlying processes. Besides numerous studies on the topic, learning Bayesian networks from real-world data remains challenging. In previous studies, e.g. on earthquake induced ground motion and flood damage assessments, we tackled the problems arising with continuous variables
A Bayesian concept learning approach to crowdsourcing
DEFF Research Database (Denmark)
Viappiani, P.; Zilles, S.; Hamilton, H.J.
2011-01-01
techniques, inference methods, and query selection strategies to assist a user charged with choosing a configuration that satisfies some (partially known) concept. Our model is able to simultaneously learn the concept definition and the types of the experts. We evaluate our model with simulations, showing......We develop a Bayesian approach to concept learning for crowdsourcing applications. A probabilistic belief over possible concept definitions is maintained and updated according to (noisy) observations from experts, whose behaviors are modeled using discrete types. We propose recommendation...
Learning Bayesian Networks with Incomplete Data by Augmentation
Adel, Tameem; de Campos, Cassio P.
2016-01-01
We present new algorithms for learning Bayesian networks from data with missing values using a data augmentation approach. An exact Bayesian network learning algorithm is obtained by recasting the problem into a standard Bayesian network learning problem without missing data. To the best of our knowledge, this is the first exact algorithm for this problem. As expected, the exact algorithm does not scale to large domains. We build on the exact method to create an approximate algorithm using a ...
Optimized Bayesian dynamic advising theory and algorithms
Karny, Miroslav
2006-01-01
Written by one of the world's leading groups in the area of Bayesian identification, control, and decision making, this book provides the theoretical and algorithmic basis of optimized probabilistic advising. Starting from abstract ideas and formulations, and culminating in detailed algorithms, the book comprises a unified treatment of an important problem of the design of advisory systems supporting supervisors of complex processes. It introduces the theoretical and algorithmic basis of developed advising, relying on novel and powerful combination black-box modelling by dynamic mixture models
On local optima in learning bayesian networks
DEFF Research Database (Denmark)
Dalgaard, Jens; Kocka, Tomas; Pena, Jose
2003-01-01
This paper proposes and evaluates the k-greedy equivalence search algorithm (KES) for learning Bayesian networks (BNs) from complete data. The main characteristic of KES is that it allows a trade-off between greediness and randomness, thus exploring different good local optima. When greediness...... is set at maximum, KES corresponds to the greedy equivalence search algorithm (GES). When greediness is kept at minimum, we prove that under mild assumptions KES asymptotically returns any inclusion optimal BN with nonzero probability. Experimental results for both synthetic and real data are reported...
Learning Local Components to Understand Large Bayesian Networks
DEFF Research Database (Denmark)
Zeng, Yifeng; Xiang, Yanping; Cordero, Jorge
2009-01-01
(domain experts) to extract accurate information from a large Bayesian network due to dimensional difficulty. We define a formulation of local components and propose a clustering algorithm to learn such local components given complete data. The algorithm groups together most inter-relevant attributes......Bayesian networks are known for providing an intuitive and compact representation of probabilistic information and allowing the creation of models over a large and complex domain. Bayesian learning and reasoning are nontrivial for a large Bayesian network. In parallel, it is a tough job for users...... in a domain. We evaluate its performance on three benchmark Bayesian networks and provide results in support. We further show that the learned components may represent local knowledge more precisely in comparison to the full Bayesian networks when working with a small amount of data....
Approximation methods for efficient learning of Bayesian networks
Riggelsen, C
2008-01-01
This publication offers and investigates efficient Monte Carlo simulation methods in order to realize a Bayesian approach to approximate learning of Bayesian networks from both complete and incomplete data. For large amounts of incomplete data when Monte Carlo methods are inefficient, approximations are implemented, such that learning remains feasible, albeit non-Bayesian. The topics discussed are: basic concepts about probabilities, graph theory and conditional independence; Bayesian network learning from data; Monte Carlo simulation techniques; and, the concept of incomplete data. In order to provide a coherent treatment of matters, thereby helping the reader to gain a thorough understanding of the whole concept of learning Bayesian networks from (in)complete data, this publication combines in a clarifying way all the issues presented in the papers with previously unpublished work.
Non-homogeneous dynamic Bayesian networks for continuous data
Grzegorczyk, Marco; Husmeier, Dirk
Classical dynamic Bayesian networks (DBNs) are based on the homogeneous Markov assumption and cannot deal with non-homogeneous temporal processes. Various approaches to relax the homogeneity assumption have recently been proposed. The present paper presents a combination of a Bayesian network with
Bayesian analysis of magnetic island dynamics
International Nuclear Information System (INIS)
Preuss, R.; Maraschek, M.; Zohm, H.; Dose, V.
2003-01-01
We examine a first order differential equation with respect to time used to describe magnetic islands in magnetically confined plasmas. The free parameters of this equation are obtained by employing Bayesian probability theory. Additionally, a typical Bayesian change point is solved in the process of obtaining the data
Filtering in Hybrid Dynamic Bayesian Networks
Andersen, Morten Nonboe; Andersen, Rasmus Orum; Wheeler, Kevin
2000-01-01
We implement a 2-time slice dynamic Bayesian network (2T-DBN) framework and make a 1-D state estimation simulation, an extension of the experiment in (v.d. Merwe et al., 2000) and compare different filtering techniques. Furthermore, we demonstrate experimentally that inference in a complex hybrid DBN is possible by simulating fault detection in a watertank system, an extension of the experiment in (Koller & Lerner, 2000) using a hybrid 2T-DBN. In both experiments, we perform approximate inference using standard filtering techniques, Monte Carlo methods and combinations of these. In the watertank simulation, we also demonstrate the use of 'non-strict' Rao-Blackwellisation. We show that the unscented Kalman filter (UKF) and UKF in a particle filtering framework outperform the generic particle filter, the extended Kalman filter (EKF) and EKF in a particle filtering framework with respect to accuracy in terms of estimation RMSE and sensitivity with respect to choice of network structure. Especially we demonstrate the superiority of UKF in a PF framework when our beliefs of how data was generated are wrong. Furthermore, we investigate the influence of data noise in the watertank simulation using UKF and PFUKD and show that the algorithms are more sensitive to changes in the measurement noise level that the process noise level. Theory and implementation is based on (v.d. Merwe et al., 2000).
Integrating distributed Bayesian inference and reinforcement learning for sensor management
Grappiolo, C.; Whiteson, S.; Pavlin, G.; Bakker, B.
2009-01-01
This paper introduces a sensor management approach that integrates distributed Bayesian inference (DBI) and reinforcement learning (RL). DBI is implemented using distributed perception networks (DPNs), a multiagent approach to performing efficient inference, while RL is used to automatically
A Bayesian Approach for Structural Learning with Hidden Markov Models
Directory of Open Access Journals (Sweden)
Cen Li
2002-01-01
Full Text Available Hidden Markov Models(HMM have proved to be a successful modeling paradigm for dynamic and spatial processes in many domains, such as speech recognition, genomics, and general sequence alignment. Typically, in these applications, the model structures are predefined by domain experts. Therefore, the HMM learning problem focuses on the learning of the parameter values of the model to fit the given data sequences. However, when one considers other domains, such as, economics and physiology, model structure capturing the system dynamic behavior is not available. In order to successfully apply the HMM methodology in these domains, it is important that a mechanism is available for automatically deriving the model structure from the data. This paper presents a HMM learning procedure that simultaneously learns the model structure and the maximum likelihood parameter values of a HMM from data. The HMM model structures are derived based on the Bayesian model selection methodology. In addition, we introduce a new initialization procedure for HMM parameter value estimation based on the K-means clustering method. Experimental results with artificially generated data show the effectiveness of the approach.
Advances in Bayesian Model Based Clustering Using Particle Learning
Energy Technology Data Exchange (ETDEWEB)
Merl, D M
2009-11-19
Recent work by Carvalho, Johannes, Lopes and Polson and Carvalho, Lopes, Polson and Taddy introduced a sequential Monte Carlo (SMC) alternative to traditional iterative Monte Carlo strategies (e.g. MCMC and EM) for Bayesian inference for a large class of dynamic models. The basis of SMC techniques involves representing the underlying inference problem as one of state space estimation, thus giving way to inference via particle filtering. The key insight of Carvalho et al was to construct the sequence of filtering distributions so as to make use of the posterior predictive distribution of the observable, a distribution usually only accessible in certain Bayesian settings. Access to this distribution allows a reversal of the usual propagate and resample steps characteristic of many SMC methods, thereby alleviating to a large extent many problems associated with particle degeneration. Furthermore, Carvalho et al point out that for many conjugate models the posterior distribution of the static variables can be parametrized in terms of [recursively defined] sufficient statistics of the previously observed data. For models where such sufficient statistics exist, particle learning as it is being called, is especially well suited for the analysis of streaming data do to the relative invariance of its algorithmic complexity with the number of data observations. Through a particle learning approach, a statistical model can be fit to data as the data is arriving, allowing at any instant during the observation process direct quantification of uncertainty surrounding underlying model parameters. Here we describe the use of a particle learning approach for fitting a standard Bayesian semiparametric mixture model as described in Carvalho, Lopes, Polson and Taddy. In Section 2 we briefly review the previously presented particle learning algorithm for the case of a Dirichlet process mixture of multivariate normals. In Section 3 we describe several novel extensions to the original
A Decomposition Algorithm for Learning Bayesian Network Structures from Data
DEFF Research Database (Denmark)
Zeng, Yifeng; Cordero Hernandez, Jorge
2008-01-01
It is a challenging task of learning a large Bayesian network from a small data set. Most conventional structural learning approaches run into the computational as well as the statistical problems. We propose a decomposition algorithm for the structure construction without having to learn...... the complete network. The new learning algorithm firstly finds local components from the data, and then recover the complete network by joining the learned components. We show the empirical performance of the decomposition algorithm in several benchmark networks....
Optimal execution in high-frequency trading with Bayesian learning
Du, Bian; Zhu, Hongliang; Zhao, Jingdong
2016-11-01
We consider optimal trading strategies in which traders submit bid and ask quotes to maximize the expected quadratic utility of total terminal wealth in a limit order book. The trader's bid and ask quotes will be changed by the Poisson arrival of market orders. Meanwhile, the trader may update his estimate of other traders' target sizes and directions by Bayesian learning. The solution of optimal execution in the limit order book is a two-step procedure. First, we model an inactive trading with no limit order in the market. The dealer simply holds dollars and shares of stocks until terminal time. Second, he calibrates his bid and ask quotes to the limit order book. The optimal solutions are given by dynamic programming and in fact they are globally optimal. We also give numerical simulation to the value function and optimal quotes at the last part of the article.
Maritime piracy situation modelling with dynamic Bayesian networks
CSIR Research Space (South Africa)
Dabrowski, James M
2015-05-01
Full Text Available A generative model for modelling maritime vessel behaviour is proposed. The model is a novel variant of the dynamic Bayesian network (DBN). The proposed DBN is in the form of a switching linear dynamic system (SLDS) that has been extended into a...
Bayesian Analysis of Individual Level Personality Dynamics
Directory of Open Access Journals (Sweden)
Edward Cripps
2016-07-01
Full Text Available A Bayesian technique with analyses of within-person processes at the level of the individual is presented. The approach is used to examine if the patterns of within-person responses on a 12 trial simulation task are consistent with the predictions of ITA theory (Dweck, 1999. ITA theory states that the performance of an individual with an entity theory of ability is more likely to spiral down following a failure experience than the performance of an individual with an incremental theory of ability. This is because entity theorists interpret failure experiences as evidence of a lack of ability, which they believe is largely innate and therefore relatively ﬁxed; whilst incremental theorists believe in the malleability of abilities and interpret failure experiences as evidence of more controllable factors such as poor strategy or lack of effort. The results of our analyses support ITA theory at both the within- and between-person levels of analyses and demonstrate the beneﬁts of Bayesian techniques for the analysis of within-person processes. These include more formal speciﬁcation of the theory and the ability to draw inferences about each individual, which allows for more nuanced interpretations of individuals within a personality category, such as differences in the individual probabilities of spiralling. While Bayesian techniques have many potential advantages for the analyses of within-person processes at the individual level, ease of use is not one of them for psychologists trained in traditional frequentist statistical techniques.
Development of dynamic Bayesian models for web application test management
Azarnova, T. V.; Polukhin, P. V.; Bondarenko, Yu V.; Kashirina, I. L.
2018-03-01
The mathematical apparatus of dynamic Bayesian networks is an effective and technically proven tool that can be used to model complex stochastic dynamic processes. According to the results of the research, mathematical models and methods of dynamic Bayesian networks provide a high coverage of stochastic tasks associated with error testing in multiuser software products operated in a dynamically changing environment. Formalized representation of the discrete test process as a dynamic Bayesian model allows us to organize the logical connection between individual test assets for multiple time slices. This approach gives an opportunity to present testing as a discrete process with set structural components responsible for the generation of test assets. Dynamic Bayesian network-based models allow us to combine in one management area individual units and testing components with different functionalities and a direct influence on each other in the process of comprehensive testing of various groups of computer bugs. The application of the proposed models provides an opportunity to use a consistent approach to formalize test principles and procedures, methods used to treat situational error signs, and methods used to produce analytical conclusions based on test results.
Robust Learning of Fixed-Structure Bayesian Networks
Diakonikolas, Ilias; Kane, Daniel; Stewart, Alistair
2016-01-01
We investigate the problem of learning Bayesian networks in an agnostic model where an $\\epsilon$-fraction of the samples are adversarially corrupted. Our agnostic learning model is similar to -- in fact, stronger than -- Huber's contamination model in robust statistics. In this work, we study the fully observable Bernoulli case where the structure of the network is given. Even in this basic setting, previous learning algorithms either run in exponential time or lose dimension-dependent facto...
Seismic Signal Compression Using Nonparametric Bayesian Dictionary Learning via Clustering
Directory of Open Access Journals (Sweden)
Xin Tian
2017-06-01
Full Text Available We introduce a seismic signal compression method based on nonparametric Bayesian dictionary learning method via clustering. The seismic data is compressed patch by patch, and the dictionary is learned online. Clustering is introduced for dictionary learning. A set of dictionaries could be generated, and each dictionary is used for one cluster’s sparse coding. In this way, the signals in one cluster could be well represented by their corresponding dictionaries. A nonparametric Bayesian dictionary learning method is used to learn the dictionaries, which naturally infers an appropriate dictionary size for each cluster. A uniform quantizer and an adaptive arithmetic coding algorithm are adopted to code the sparse coefficients. With comparisons to other state-of-the art approaches, the effectiveness of the proposed method could be validated in the experiments.
A Bayesian foundation for individual learning under uncertainty
Directory of Open Access Journals (Sweden)
Christoph eMathys
2011-05-01
Full Text Available Computational learning models are critical for understanding mechanisms of adaptive behavior. However, the two major current frameworks, reinforcement learning (RL and Bayesian learning, both have certain limitations. For example, many Bayesian models are agnostic of inter-individual variability and involve complicated integrals, making online learning difficult. Here, we introduce a generic hierarchical Bayesian framework for individual learning under multiple forms of uncertainty (e.g., environmental volatility and perceptual uncertainty. The model assumes Gaussian random walks of states at all but the first level, with the step size determined by the next higher level. The coupling between levels is controlled by parameters that shape the influence of uncertainty on learning in a subject-specific fashion. Using variational Bayes under a mean field approximation and a novel approximation to the posterior energy function, we derive trial-by-trial update equations which (i are analytical and extremely efficient, enabling real-time learning, (ii have a natural interpretation in terms of RL, and (iii contain parameters representing processes which play a key role in current theories of learning, e.g., precision-weighting of prediction error. These parameters allow for the expression of individual differences in learning and may relate to specific neuromodulatory mechanisms in the brain. Our model is very general: it can deal with both discrete and continuous states and equally accounts for deterministic and probabilistic relations between environmental events and perceptual states (i.e., situations with and without perceptual uncertainty. These properties are illustrated by simulations and analyses of empirical time series. Overall, our framework provides a novel foundation for understanding normal and pathological learning that contextualizes RL within a generic Bayesian scheme and thus connects it to principles of optimality from probability
A bayesian foundation for individual learning under uncertainty.
Mathys, Christoph; Daunizeau, Jean; Friston, Karl J; Stephan, Klaas E
2011-01-01
Computational learning models are critical for understanding mechanisms of adaptive behavior. However, the two major current frameworks, reinforcement learning (RL) and Bayesian learning, both have certain limitations. For example, many Bayesian models are agnostic of inter-individual variability and involve complicated integrals, making online learning difficult. Here, we introduce a generic hierarchical Bayesian framework for individual learning under multiple forms of uncertainty (e.g., environmental volatility and perceptual uncertainty). The model assumes Gaussian random walks of states at all but the first level, with the step size determined by the next highest level. The coupling between levels is controlled by parameters that shape the influence of uncertainty on learning in a subject-specific fashion. Using variational Bayes under a mean-field approximation and a novel approximation to the posterior energy function, we derive trial-by-trial update equations which (i) are analytical and extremely efficient, enabling real-time learning, (ii) have a natural interpretation in terms of RL, and (iii) contain parameters representing processes which play a key role in current theories of learning, e.g., precision-weighting of prediction error. These parameters allow for the expression of individual differences in learning and may relate to specific neuromodulatory mechanisms in the brain. Our model is very general: it can deal with both discrete and continuous states and equally accounts for deterministic and probabilistic relations between environmental events and perceptual states (i.e., situations with and without perceptual uncertainty). These properties are illustrated by simulations and analyses of empirical time series. Overall, our framework provides a novel foundation for understanding normal and pathological learning that contextualizes RL within a generic Bayesian scheme and thus connects it to principles of optimality from probability theory.
Learning Negotiation Policies Using IB3 and Bayesian Networks
Nalepa, Gislaine M.; Ávila, Bráulio C.; Enembreck, Fabrício; Scalabrin, Edson E.
This paper presents an intelligent offer policy in a negotiation environment, in which each agent involved learns the preferences of its opponent in order to improve its own performance. Each agent must also be able to detect drifts in the opponent's preferences so as to quickly adjust itself to their new offer policy. For this purpose, two simple learning techniques were first evaluated: (i) based on instances (IB3) and (ii) based on Bayesian Networks. Additionally, as its known that in theory group learning produces better results than individual/single learning, the efficiency of IB3 and Bayesian classifier groups were also analyzed. Finally, each decision model was evaluated in moments of concept drift, being the drift gradual, moderate or abrupt. Results showed that both groups of classifiers were able to effectively detect drifts in the opponent's preferences.
International Nuclear Information System (INIS)
Montani, S.; Portinale, L.; Bobbio, A.; Codetta-Raiteri, D.
2008-01-01
In this paper, we present RADYBAN (Reliability Analysis with DYnamic BAyesian Networks), a software tool which allows to analyze a dynamic fault tree relying on its conversion into a dynamic Bayesian network. The tool implements a modular algorithm for automatically translating a dynamic fault tree into the corresponding dynamic Bayesian network and exploits classical algorithms for the inference on dynamic Bayesian networks, in order to compute reliability measures. After having described the basic features of the tool, we show how it operates on a real world example and we compare the unreliability results it generates with those returned by other methodologies, in order to verify the correctness and the consistency of the results obtained
Impact of censoring on learning Bayesian networks in survival modelling.
Stajduhar, Ivan; Dalbelo-Basić, Bojana; Bogunović, Nikola
2009-11-01
Bayesian networks are commonly used for presenting uncertainty and covariate interactions in an easily interpretable way. Because of their efficient inference and ability to represent causal relationships, they are an excellent choice for medical decision support systems in diagnosis, treatment, and prognosis. Although good procedures for learning Bayesian networks from data have been defined, their performance in learning from censored survival data has not been widely studied. In this paper, we explore how to use these procedures to learn about possible interactions between prognostic factors and their influence on the variate of interest. We study how censoring affects the probability of learning correct Bayesian network structures. Additionally, we analyse the potential usefulness of the learnt models for predicting the time-independent probability of an event of interest. We analysed the influence of censoring with a simulation on synthetic data sampled from randomly generated Bayesian networks. We used two well-known methods for learning Bayesian networks from data: a constraint-based method and a score-based method. We compared the performance of each method under different levels of censoring to those of the naive Bayes classifier and the proportional hazards model. We did additional experiments on several datasets from real-world medical domains. The machine-learning methods treated censored cases in the data as event-free. We report and compare results for several commonly used model evaluation metrics. On average, the proportional hazards method outperformed other methods in most censoring setups. As part of the simulation study, we also analysed structural similarities of the learnt networks. Heavy censoring, as opposed to no censoring, produces up to a 5% surplus and up to 10% missing total arcs. It also produces up to 50% missing arcs that should originally be connected to the variate of interest. Presented methods for learning Bayesian networks from
Theory-based Bayesian models of inductive learning and reasoning.
Tenenbaum, Joshua B; Griffiths, Thomas L; Kemp, Charles
2006-07-01
Inductive inference allows humans to make powerful generalizations from sparse data when learning about word meanings, unobserved properties, causal relationships, and many other aspects of the world. Traditional accounts of induction emphasize either the power of statistical learning, or the importance of strong constraints from structured domain knowledge, intuitive theories or schemas. We argue that both components are necessary to explain the nature, use and acquisition of human knowledge, and we introduce a theory-based Bayesian framework for modeling inductive learning and reasoning as statistical inferences over structured knowledge representations.
Dynamic model based on Bayesian method for energy security assessment
International Nuclear Information System (INIS)
Augutis, Juozas; Krikštolaitis, Ričardas; Pečiulytė, Sigita; Žutautaitė, Inga
2015-01-01
Highlights: • Methodology for dynamic indicator model construction and forecasting of indicators. • Application of dynamic indicator model for energy system development scenarios. • Expert judgement involvement using Bayesian method. - Abstract: The methodology for the dynamic indicator model construction and forecasting of indicators for the assessment of energy security level is presented in this article. An indicator is a special index, which provides numerical values to important factors for the investigated area. In real life, models of different processes take into account various factors that are time-dependent and dependent on each other. Thus, it is advisable to construct a dynamic model in order to describe these dependences. The energy security indicators are used as factors in the dynamic model. Usually, the values of indicators are obtained from statistical data. The developed dynamic model enables to forecast indicators’ variation taking into account changes in system configuration. The energy system development is usually based on a new object construction. Since the parameters of changes of the new system are not exactly known, information about their influences on indicators could not be involved in the model by deterministic methods. Thus, dynamic indicators’ model based on historical data is adjusted by probabilistic model with the influence of new factors on indicators using the Bayesian method
Bayesian nonparametric dictionary learning for compressed sensing MRI.
Huang, Yue; Paisley, John; Lin, Qin; Ding, Xinghao; Fu, Xueyang; Zhang, Xiao-Ping
2014-12-01
We develop a Bayesian nonparametric model for reconstructing magnetic resonance images (MRIs) from highly undersampled k -space data. We perform dictionary learning as part of the image reconstruction process. To this end, we use the beta process as a nonparametric dictionary learning prior for representing an image patch as a sparse combination of dictionary elements. The size of the dictionary and patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables. Dictionary learning is performed directly on the compressed image, and so is tailored to the MRI being considered. In addition, we investigate a total variation penalty term in combination with the dictionary learning model, and show how the denoising property of dictionary learning removes dependence on regularization parameters in the noisy setting. We derive a stochastic optimization algorithm based on Markov chain Monte Carlo for the Bayesian model, and use the alternating direction method of multipliers for efficiently performing total variation minimization. We present empirical results on several MRI, which show that the proposed regularization framework can improve reconstruction accuracy over other methods.
A Dynamic Bayesian Approach to Computational Laban Shape Quality Analysis
Directory of Open Access Journals (Sweden)
Dilip Swaminathan
2009-01-01
kinesiology. LMA (especially Effort/Shape emphasizes how internal feelings and intentions govern the patterning of movement throughout the whole body. As we argue, a complex understanding of intention via LMA is necessary for human-computer interaction to become embodied in ways that resemble interaction in the physical world. We thus introduce a novel, flexible Bayesian fusion approach for identifying LMA Shape qualities from raw motion capture data in real time. The method uses a dynamic Bayesian network (DBN to fuse movement features across the body and across time and as we discuss can be readily adapted for low-cost video. It has delivered excellent performance in preliminary studies comprising improvisatory movements. Our approach has been incorporated in Response, a mixed-reality environment where users interact via natural, full-body human movement and enhance their bodily-kinesthetic awareness through immersive sound and light feedback, with applications to kinesiology training, Parkinson's patient rehabilitation, interactive dance, and many other areas.
Spike-Based Bayesian-Hebbian Learning of Temporal Sequences
DEFF Research Database (Denmark)
Tully, Philip J; Lindén, Henrik; Hennig, Matthias H
2016-01-01
Many cognitive and motor functions are enabled by the temporal representation and processing of stimuli, but it remains an open issue how neocortical microcircuits can reliably encode and replay such sequences of information. To better understand this, a modular attractor memory network is proposed...... in which meta-stable sequential attractor transitions are learned through changes to synaptic weights and intrinsic excitabilities via the spike-based Bayesian Confidence Propagation Neural Network (BCPNN) learning rule. We find that the formation of distributed memories, embodied by increased periods...
Daly, Rónán; Edwards, Kieron D.; O'Neill, John S.; Aitken, Stuart; Millar, Andrew J.; Girolami, Mark
Modelling gene regulatory networks in organisms is an important task that has recently become possible due to large scale assays using technologies such as microarrays. In this paper, the circadian clock of Arabidopsis thaliana is modelled by fitting dynamic Bayesian networks to luminescence data gathered from experiments. This work differs from previous modelling attempts by using higher-order dynamic Bayesian networks to explicitly model the time lag between the various genes being expressed. In order to achieve this goal, new techniques in preprocessing the data and in evaluating a learned model are proposed. It is shown that it is possible, to some extent, to model these time delays using a higher-order dynamic Bayesian network.
Sparse Bayesian Learning for DOA Estimation with Mutual Coupling
Directory of Open Access Journals (Sweden)
Jisheng Dai
2015-10-01
Full Text Available Sparse Bayesian learning (SBL has given renewed interest to the problem of direction-of-arrival (DOA estimation. It is generally assumed that the measurement matrix in SBL is precisely known. Unfortunately, this assumption may be invalid in practice due to the imperfect manifold caused by unknown or misspecified mutual coupling. This paper describes a modified SBL method for joint estimation of DOAs and mutual coupling coefficients with uniform linear arrays (ULAs. Unlike the existing method that only uses stationary priors, our new approach utilizes a hierarchical form of the Student t prior to enforce the sparsity of the unknown signal more heavily. We also provide a distinct Bayesian inference for the expectation-maximization (EM algorithm, which can update the mutual coupling coefficients more efficiently. Another difference is that our method uses an additional singular value decomposition (SVD to reduce the computational complexity of the signal reconstruction process and the sensitivity to the measurement noise.
Remotely Sensed Monitoring of Small Reservoir Dynamics: A Bayesian Approach
Directory of Open Access Journals (Sweden)
Dirk Eilander
2014-01-01
Full Text Available Multipurpose small reservoirs are important for livelihoods in rural semi-arid regions. To manage and plan these reservoirs and to assess their hydrological impact at a river basin scale, it is important to monitor their water storage dynamics. This paper introduces a Bayesian approach for monitoring small reservoirs with radar satellite images. The newly developed growing Bayesian classifier has a high degree of automation, can readily be extended with auxiliary information and reduces the confusion error to the land-water boundary pixels. A case study has been performed in the Upper East Region of Ghana, based on Radarsat-2 data from November 2012 until April 2013. Results show that the growing Bayesian classifier can deal with the spatial and temporal variability in synthetic aperture radar (SAR backscatter intensities from small reservoirs. Due to its ability to incorporate auxiliary information, the algorithm is able to delineate open water from SAR imagery with a low land-water contrast in the case of wind-induced Bragg scattering or limited vegetation on the land surrounding a small reservoir.
A geometric view on learning Bayesian network structures
Czech Academy of Sciences Publication Activity Database
Studený, Milan; Vomlel, Jiří; Hemmecke, R.
2010-01-01
Roč. 51, č. 5 (2010), s. 578-586 ISSN 0888-613X. [PGM 2008] R&D Projects: GA AV ČR(CZ) IAA100750603; GA MŠk(CZ) 1M0572; GA ČR GA201/08/0539 Grant - others:GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : learning Bayesian networks * standard imset * inclusion neighborhood * geometric neighborhood * GES algorithm Subject RIV: BA - General Mathematics Impact factor: 1.679, year: 2010 http://library.utia.cas.cz/separaty/2010/MTR/studeny-0342804. pdf
Online Learning of Industrial Manipulators' Dynamics Models
DEFF Research Database (Denmark)
Polydoros, Athanasios
2017-01-01
, it was compared with multiple other state-of-the-art machine learning algorithms. Moreover, the thesis presents the application of the proposed learning method on robot control for achieving trajectory execution while learning the inverse dynamics models on-the-fly . Also it is presented the application...... of the dynamics models. Those mainly derive from physics-based methods and thus they are based on physical properties which are hard to be calculated. In this thesis, is presented, a novel online machine learning approach which is able to model both inverse and forward dynamics models of industrial manipulators....... The proposed method belongs to the class of deep learning and exploits the concepts of self-organization, recurrent neural networks and iterative multivariate Bayesian regression. It has been evaluated on multiple datasets captured from industrial robots while they were performing various tasks. Also...
Learning priors for Bayesian computations in the nervous system.
Directory of Open Access Journals (Sweden)
Max Berniker
Full Text Available Our nervous system continuously combines new information from our senses with information it has acquired throughout life. Numerous studies have found that human subjects manage this by integrating their observations with their previous experience (priors in a way that is close to the statistical optimum. However, little is known about the way the nervous system acquires or learns priors. Here we present results from experiments where the underlying distribution of target locations in an estimation task was switched, manipulating the prior subjects should use. Our experimental design allowed us to measure a subject's evolving prior while they learned. We confirm that through extensive practice subjects learn the correct prior for the task. We found that subjects can rapidly learn the mean of a new prior while the variance is learned more slowly and with a variable learning rate. In addition, we found that a Bayesian inference model could predict the time course of the observed learning while offering an intuitive explanation for the findings. The evidence suggests the nervous system continuously updates its priors to enable efficient behavior.
A Bayesian Theory of Sequential Causal Learning and Abstract Transfer.
Lu, Hongjing; Rojas, Randall R; Beckers, Tom; Yuille, Alan L
2016-03-01
Two key research issues in the field of causal learning are how people acquire causal knowledge when observing data that are presented sequentially, and the level of abstraction at which learning takes place. Does sequential causal learning solely involve the acquisition of specific cause-effect links, or do learners also acquire knowledge about abstract causal constraints? Recent empirical studies have revealed that experience with one set of causal cues can dramatically alter subsequent learning and performance with entirely different cues, suggesting that learning involves abstract transfer, and such transfer effects involve sequential presentation of distinct sets of causal cues. It has been demonstrated that pre-training (or even post-training) can modulate classic causal learning phenomena such as forward and backward blocking. To account for these effects, we propose a Bayesian theory of sequential causal learning. The theory assumes that humans are able to consider and use several alternative causal generative models, each instantiating a different causal integration rule. Model selection is used to decide which integration rule to use in a given learning environment in order to infer causal knowledge from sequential data. Detailed computer simulations demonstrate that humans rely on the abstract characteristics of outcome variables (e.g., binary vs. continuous) to select a causal integration rule, which in turn alters causal learning in a variety of blocking and overshadowing paradigms. When the nature of the outcome variable is ambiguous, humans select the model that yields the best fit with the recent environment, and then apply it to subsequent learning tasks. Based on sequential patterns of cue-outcome co-occurrence, the theory can account for a range of phenomena in sequential causal learning, including various blocking effects, primacy effects in some experimental conditions, and apparently abstract transfer of causal knowledge. Copyright © 2015
Variational Bayesian Learning for Wavelet Independent Component Analysis
Roussos, E.; Roberts, S.; Daubechies, I.
2005-11-01
In an exploratory approach to data analysis, it is often useful to consider the observations as generated from a set of latent generators or "sources" via a generally unknown mapping. For the noisy overcomplete case, where we have more sources than observations, the problem becomes extremely ill-posed. Solutions to such inverse problems can, in many cases, be achieved by incorporating prior knowledge about the problem, captured in the form of constraints. This setting is a natural candidate for the application of the Bayesian methodology, allowing us to incorporate "soft" constraints in a natural manner. The work described in this paper is mainly driven by problems in functional magnetic resonance imaging of the brain, for the neuro-scientific goal of extracting relevant "maps" from the data. This can be stated as a `blind' source separation problem. Recent experiments in the field of neuroscience show that these maps are sparse, in some appropriate sense. The separation problem can be solved by independent component analysis (ICA), viewed as a technique for seeking sparse components, assuming appropriate distributions for the sources. We derive a hybrid wavelet-ICA model, transforming the signals into a domain where the modeling assumption of sparsity of the coefficients with respect to a dictionary is natural. We follow a graphical modeling formalism, viewing ICA as a probabilistic generative model. We use hierarchical source and mixing models and apply Bayesian inference to the problem. This allows us to perform model selection in order to infer the complexity of the representation, as well as automatic denoising. Since exact inference and learning in such a model is intractable, we follow a variational Bayesian mean-field approach in the conjugate-exponential family of distributions, for efficient unsupervised learning in multi-dimensional settings. The performance of the proposed algorithm is demonstrated on some representative experiments.
BDgraph: An R Package for Bayesian Structure Learning in Graphical Models
Mohammadi, A.; Wit, E.C.
2017-01-01
Graphical models provide powerful tools to uncover complicated patterns in multivariate data and are commonly used in Bayesian statistics and machine learning. In this paper, we introduce an R package BDgraph which performs Bayesian structure learning for general undirected graphical models with
The neighborhood MCMC sampler for learning Bayesian networks
Alyami, Salem A.; Azad, A. K. M.; Keith, Jonathan M.
2016-07-01
Getting stuck in local maxima is a problem that arises while learning Bayesian networks (BNs) structures. In this paper, we studied a recently proposed Markov chain Monte Carlo (MCMC) sampler, called the Neighbourhood sampler (NS), and examined how efficiently it can sample BNs when local maxima are present. We assume that a posterior distribution f(N,E|D) has been defined, where D represents data relevant to the inference, N and E are the sets of nodes and directed edges, respectively. We illustrate the new approach by sampling from such a distribution, and inferring BNs. The simulations conducted in this paper show that the new learning approach substantially avoids getting stuck in local modes of the distribution, and achieves a more rapid rate of convergence, compared to other common algorithms e.g. the MCMC Metropolis-Hastings sampler.
Bayesian inversion analysis of nonlinear dynamics in surface heterogeneous reactions.
Omori, Toshiaki; Kuwatani, Tatsu; Okamoto, Atsushi; Hukushima, Koji
2016-09-01
It is essential to extract nonlinear dynamics from time-series data as an inverse problem in natural sciences. We propose a Bayesian statistical framework for extracting nonlinear dynamics of surface heterogeneous reactions from sparse and noisy observable data. Surface heterogeneous reactions are chemical reactions with conjugation of multiple phases, and they have the intrinsic nonlinearity of their dynamics caused by the effect of surface-area between different phases. We adapt a belief propagation method and an expectation-maximization (EM) algorithm to partial observation problem, in order to simultaneously estimate the time course of hidden variables and the kinetic parameters underlying dynamics. The proposed belief propagation method is performed by using sequential Monte Carlo algorithm in order to estimate nonlinear dynamical system. Using our proposed method, we show that the rate constants of dissolution and precipitation reactions, which are typical examples of surface heterogeneous reactions, as well as the temporal changes of solid reactants and products, were successfully estimated only from the observable temporal changes in the concentration of the dissolved intermediate product.
Dynamic safety assessment of natural gas stations using Bayesian network
International Nuclear Information System (INIS)
Zarei, Esmaeil; Azadeh, Ali; Khakzad, Nima; Aliabadi, Mostafa Mirzaei; Mohammadfam, Iraj
2017-01-01
Graphical abstract: Dynamic cause-consequence analysis of the regulator system failure using BN. - Highlights: • A dynamic and comprehensive QRA (DCQRA) framework is proposed for safety assessment of CGSs. • Bow-tie diagram and Bayesian network are employed for accident scenario modeling. • Critical basic events and minimal cut sets are identified using probability updating. - Abstract: Pipelines are one of the most popular and effective ways of transporting hazardous materials, especially natural gas. However, the rapid development of gas pipelines and stations in urban areas has introduced a serious threat to public safety and assets. Although different methods have been developed for risk analysis of gas transportation systems, a comprehensive methodology for risk analysis is still lacking, especially in natural gas stations. The present work is aimed at developing a dynamic and comprehensive quantitative risk analysis (DCQRA) approach for accident scenario and risk modeling of natural gas stations. In this approach, a FMEA is used for hazard analysis while a Bow-tie diagram and Bayesian network are employed to model the worst-case accident scenario and to assess the risks. The results have indicated that the failure of the regulator system was the worst-case accident scenario with the human error as the most contributing factor. Thus, in risk management plan of natural gas stations, priority should be given to the most probable root events and main contribution factors, which have identified in the present study, in order to reduce the occurrence probability of the accident scenarios and thus alleviate the risks.
Dynamic safety assessment of natural gas stations using Bayesian network
Energy Technology Data Exchange (ETDEWEB)
Zarei, Esmaeil, E-mail: smlzarei65@gmail.com [Center of Excellence for Occupational Health Engineering, Research Center for Health Sciences, Faculty of Health, Hamadan University of Medical Sciences, Hamadan (Iran, Islamic Republic of); Azadeh, Ali [School of Industrial and Systems Engineering, Center of Excellence for Intelligent-Based Experimental Mechanic, College of Engineering, University of Tehran (Iran, Islamic Republic of); Khakzad, Nima [Safety and Security Science Section, Delft University of Technology, Delft (Netherlands); Aliabadi, Mostafa Mirzaei [Center of Excellence for Occupational Health Engineering, Research Center for Health Sciences, Faculty of Health, Hamadan University of Medical Sciences, Hamadan (Iran, Islamic Republic of); Mohammadfam, Iraj, E-mail: mohammadfam@umsha.ac.ir [Center of Excellence for Occupational Health Engineering, Research Center for Health Sciences, Faculty of Health, Hamadan University of Medical Sciences, Hamadan (Iran, Islamic Republic of)
2017-01-05
Graphical abstract: Dynamic cause-consequence analysis of the regulator system failure using BN. - Highlights: • A dynamic and comprehensive QRA (DCQRA) framework is proposed for safety assessment of CGSs. • Bow-tie diagram and Bayesian network are employed for accident scenario modeling. • Critical basic events and minimal cut sets are identified using probability updating. - Abstract: Pipelines are one of the most popular and effective ways of transporting hazardous materials, especially natural gas. However, the rapid development of gas pipelines and stations in urban areas has introduced a serious threat to public safety and assets. Although different methods have been developed for risk analysis of gas transportation systems, a comprehensive methodology for risk analysis is still lacking, especially in natural gas stations. The present work is aimed at developing a dynamic and comprehensive quantitative risk analysis (DCQRA) approach for accident scenario and risk modeling of natural gas stations. In this approach, a FMEA is used for hazard analysis while a Bow-tie diagram and Bayesian network are employed to model the worst-case accident scenario and to assess the risks. The results have indicated that the failure of the regulator system was the worst-case accident scenario with the human error as the most contributing factor. Thus, in risk management plan of natural gas stations, priority should be given to the most probable root events and main contribution factors, which have identified in the present study, in order to reduce the occurrence probability of the accident scenarios and thus alleviate the risks.
Inferring on the Intentions of Others by Hierarchical Bayesian Learning
Diaconescu, Andreea O.; Mathys, Christoph; Weber, Lilian A. E.; Daunizeau, Jean; Kasper, Lars; Lomakina, Ekaterina I.; Fehr, Ernst; Stephan, Klaas E.
2014-01-01
Inferring on others' (potentially time-varying) intentions is a fundamental problem during many social transactions. To investigate the underlying mechanisms, we applied computational modeling to behavioral data from an economic game in which 16 pairs of volunteers (randomly assigned to “player” or “adviser” roles) interacted. The player performed a probabilistic reinforcement learning task, receiving information about a binary lottery from a visual pie chart. The adviser, who received more predictive information, issued an additional recommendation. Critically, the game was structured such that the adviser's incentives to provide helpful or misleading information varied in time. Using a meta-Bayesian modeling framework, we found that the players' behavior was best explained by the deployment of hierarchical learning: they inferred upon the volatility of the advisers' intentions in order to optimize their predictions about the validity of their advice. Beyond learning, volatility estimates also affected the trial-by-trial variability of decisions: participants were more likely to rely on their estimates of advice accuracy for making choices when they believed that the adviser's intentions were presently stable. Finally, our model of the players' inference predicted the players' interpersonal reactivity index (IRI) scores, explicit ratings of the advisers' helpfulness and the advisers' self-reports on their chosen strategy. Overall, our results suggest that humans (i) employ hierarchical generative models to infer on the changing intentions of others, (ii) use volatility estimates to inform decision-making in social interactions, and (iii) integrate estimates of advice accuracy with non-social sources of information. The Bayesian framework presented here can quantify individual differences in these mechanisms from simple behavioral readouts and may prove useful in future clinical studies of maladaptive social cognition. PMID:25187943
Learning Predictive Interactions Using Information Gain and Bayesian Network Scoring.
Directory of Open Access Journals (Sweden)
Xia Jiang
Full Text Available The problems of correlation and classification are long-standing in the fields of statistics and machine learning, and techniques have been developed to address these problems. We are now in the era of high-dimensional data, which is data that can concern billions of variables. These data present new challenges. In particular, it is difficult to discover predictive variables, when each variable has little marginal effect. An example concerns Genome-wide Association Studies (GWAS datasets, which involve millions of single nucleotide polymorphism (SNPs, where some of the SNPs interact epistatically to affect disease status. Towards determining these interacting SNPs, researchers developed techniques that addressed this specific problem. However, the problem is more general, and so these techniques are applicable to other problems concerning interactions. A difficulty with many of these techniques is that they do not distinguish whether a learned interaction is actually an interaction or whether it involves several variables with strong marginal effects.We address this problem using information gain and Bayesian network scoring. First, we identify candidate interactions by determining whether together variables provide more information than they do separately. Then we use Bayesian network scoring to see if a candidate interaction really is a likely model. Our strategy is called MBS-IGain. Using 100 simulated datasets and a real GWAS Alzheimer's dataset, we investigated the performance of MBS-IGain.When analyzing the simulated datasets, MBS-IGain substantially out-performed nine previous methods at locating interacting predictors, and at identifying interactions exactly. When analyzing the real Alzheimer's dataset, we obtained new results and results that substantiated previous findings. We conclude that MBS-IGain is highly effective at finding interactions in high-dimensional datasets. This result is significant because we have increasingly
Aggregated Residential Load Modeling Using Dynamic Bayesian Networks
Energy Technology Data Exchange (ETDEWEB)
Vlachopoulou, Maria; Chin, George; Fuller, Jason C.; Lu, Shuai
2014-09-28
Abstract—It is already obvious that the future power grid will have to address higher demand for power and energy, and to incorporate renewable resources of different energy generation patterns. Demand response (DR) schemes could successfully be used to manage and balance power supply and demand under operating conditions of the future power grid. To achieve that, more advanced tools for DR management of operations and planning are necessary that can estimate the available capacity from DR resources. In this research, a Dynamic Bayesian Network (DBN) is derived, trained, and tested that can model aggregated load of Heating, Ventilation, and Air Conditioning (HVAC) systems. DBNs can provide flexible and powerful tools for both operations and planing, due to their unique analytical capabilities. The DBN model accuracy and flexibility of use is demonstrated by testing the model under different operational scenarios.
Dynamic Bayesian Networks for Context-Aware Fall Risk Assessment
Directory of Open Access Journals (Sweden)
Gregory Koshmak
2014-05-01
Full Text Available Fall incidents among the elderly often occur in the home and can cause serious injuries affecting their independent living. This paper presents an approach where data from wearable sensors integrated in a smart home environment is combined using a dynamic Bayesian network. The smart home environment provides contextual data, obtained from environmental sensors, and contributes to assessing a fall risk probability. The evaluation of the developed system is performed through simulation. Each time step is represented by a single user activity and interacts with a fall sensors located on a mobile device. A posterior probability is calculated for each recognized activity or contextual information. The output of the system provides a total risk assessment of falling given a response from the fall sensor.
Inference algorithms and learning theory for Bayesian sparse factor analysis
International Nuclear Information System (INIS)
Rattray, Magnus; Sharp, Kevin; Stegle, Oliver; Winn, John
2009-01-01
Bayesian sparse factor analysis has many applications; for example, it has been applied to the problem of inferring a sparse regulatory network from gene expression data. We describe a number of inference algorithms for Bayesian sparse factor analysis using a slab and spike mixture prior. These include well-established Markov chain Monte Carlo (MCMC) and variational Bayes (VB) algorithms as well as a novel hybrid of VB and Expectation Propagation (EP). For the case of a single latent factor we derive a theory for learning performance using the replica method. We compare the MCMC and VB/EP algorithm results with simulated data to the theoretical prediction. The results for MCMC agree closely with the theory as expected. Results for VB/EP are slightly sub-optimal but show that the new algorithm is effective for sparse inference. In large-scale problems MCMC is infeasible due to computational limitations and the VB/EP algorithm then provides a very useful computationally efficient alternative.
Inference algorithms and learning theory for Bayesian sparse factor analysis
Energy Technology Data Exchange (ETDEWEB)
Rattray, Magnus; Sharp, Kevin [School of Computer Science, University of Manchester, Manchester M13 9PL (United Kingdom); Stegle, Oliver [Max-Planck-Institute for Biological Cybernetics, Tuebingen (Germany); Winn, John, E-mail: magnus.rattray@manchester.ac.u [Microsoft Research Cambridge, Roger Needham Building, Cambridge, CB3 0FB (United Kingdom)
2009-12-01
Bayesian sparse factor analysis has many applications; for example, it has been applied to the problem of inferring a sparse regulatory network from gene expression data. We describe a number of inference algorithms for Bayesian sparse factor analysis using a slab and spike mixture prior. These include well-established Markov chain Monte Carlo (MCMC) and variational Bayes (VB) algorithms as well as a novel hybrid of VB and Expectation Propagation (EP). For the case of a single latent factor we derive a theory for learning performance using the replica method. We compare the MCMC and VB/EP algorithm results with simulated data to the theoretical prediction. The results for MCMC agree closely with the theory as expected. Results for VB/EP are slightly sub-optimal but show that the new algorithm is effective for sparse inference. In large-scale problems MCMC is infeasible due to computational limitations and the VB/EP algorithm then provides a very useful computationally efficient alternative.
Spike-Based Bayesian-Hebbian Learning of Temporal Sequences.
Directory of Open Access Journals (Sweden)
Philip J Tully
2016-05-01
Full Text Available Many cognitive and motor functions are enabled by the temporal representation and processing of stimuli, but it remains an open issue how neocortical microcircuits can reliably encode and replay such sequences of information. To better understand this, a modular attractor memory network is proposed in which meta-stable sequential attractor transitions are learned through changes to synaptic weights and intrinsic excitabilities via the spike-based Bayesian Confidence Propagation Neural Network (BCPNN learning rule. We find that the formation of distributed memories, embodied by increased periods of firing in pools of excitatory neurons, together with asymmetrical associations between these distinct network states, can be acquired through plasticity. The model's feasibility is demonstrated using simulations of adaptive exponential integrate-and-fire model neurons (AdEx. We show that the learning and speed of sequence replay depends on a confluence of biophysically relevant parameters including stimulus duration, level of background noise, ratio of synaptic currents, and strengths of short-term depression and adaptation. Moreover, sequence elements are shown to flexibly participate multiple times in the sequence, suggesting that spiking attractor networks of this type can support an efficient combinatorial code. The model provides a principled approach towards understanding how multiple interacting plasticity mechanisms can coordinate hetero-associative learning in unison.
Markov Chain Monte Carlo Bayesian Learning for Neural Networks
Goodrich, Michael S.
2011-01-01
Conventional training methods for neural networks involve starting al a random location in the solution space of the network weights, navigating an error hyper surface to reach a minimum, and sometime stochastic based techniques (e.g., genetic algorithms) to avoid entrapment in a local minimum. It is further typically necessary to preprocess the data (e.g., normalization) to keep the training algorithm on course. Conversely, Bayesian based learning is an epistemological approach concerned with formally updating the plausibility of competing candidate hypotheses thereby obtaining a posterior distribution for the network weights conditioned on the available data and a prior distribution. In this paper, we developed a powerful methodology for estimating the full residual uncertainty in network weights and therefore network predictions by using a modified Jeffery's prior combined with a Metropolis Markov Chain Monte Carlo method.
Modelling of population dynamics of red king crab using Bayesian approach
Directory of Open Access Journals (Sweden)
Bakanev Sergey ...
2012-10-01
Modeling population dynamics based on the Bayesian approach enables to successfully resolve the above issues. The integration of the data from various studies into a unified model based on Bayesian parameter estimation method provides a much more detailed description of the processes occurring in the population.
Dynamic Bayesian Network Modeling of Game Based Diagnostic Assessments. CRESST Report 837
Levy, Roy
2014-01-01
Digital games offer an appealing environment for assessing student proficiencies, including skills and misconceptions in a diagnostic setting. This paper proposes a dynamic Bayesian network modeling approach for observations of student performance from an educational video game. A Bayesian approach to model construction, calibration, and use in…
Flexible Bayesian Dynamic Modeling of Covariance and Correlation Matrices
Lan, Shiwei
2017-11-08
Modeling covariance (and correlation) matrices is a challenging problem due to the large dimensionality and positive-definiteness constraint. In this paper, we propose a novel Bayesian framework based on decomposing the covariance matrix into variance and correlation matrices. The highlight is that the correlations are represented as products of vectors on unit spheres. We propose a variety of distributions on spheres (e.g. the squared-Dirichlet distribution) to induce flexible prior distributions for covariance matrices that go beyond the commonly used inverse-Wishart prior. To handle the intractability of the resulting posterior, we introduce the adaptive $\\\\Delta$-Spherical Hamiltonian Monte Carlo. We also extend our structured framework to dynamic cases and introduce unit-vector Gaussian process priors for modeling the evolution of correlation among multiple time series. Using an example of Normal-Inverse-Wishart problem, a simulated periodic process, and an analysis of local field potential data (collected from the hippocampus of rats performing a complex sequence memory task), we demonstrated the validity and effectiveness of our proposed framework for (dynamic) modeling covariance and correlation matrices.
Bayesian feature weighting for unsupervised learning, with application to object recognition
Carbonetto , Peter; De Freitas , Nando; Gustafson , Paul; Thompson , Natalie
2003-01-01
International audience; We present a method for variable selection/weighting in an unsupervised learning context using Bayesian shrinkage. The basis for the model parameters and cluster assignments can be computed simultaneous using an efficient EM algorithm. Applying our Bayesian shrinkage model to a complex problem in object recognition (Duygulu, Barnard, de Freitas and Forsyth 2002), our experiments yied good results.
Yildiz, Izzet B; von Kriegstein, Katharina; Kiebel, Stefan J
2013-01-01
Our knowledge about the computational mechanisms underlying human learning and recognition of sound sequences, especially speech, is still very limited. One difficulty in deciphering the exact means by which humans recognize speech is that there are scarce experimental findings at a neuronal, microscopic level. Here, we show that our neuronal-computational understanding of speech learning and recognition may be vastly improved by looking at an animal model, i.e., the songbird, which faces the same challenge as humans: to learn and decode complex auditory input, in an online fashion. Motivated by striking similarities between the human and songbird neural recognition systems at the macroscopic level, we assumed that the human brain uses the same computational principles at a microscopic level and translated a birdsong model into a novel human sound learning and recognition model with an emphasis on speech. We show that the resulting Bayesian model with a hierarchy of nonlinear dynamical systems can learn speech samples such as words rapidly and recognize them robustly, even in adverse conditions. In addition, we show that recognition can be performed even when words are spoken by different speakers and with different accents-an everyday situation in which current state-of-the-art speech recognition models often fail. The model can also be used to qualitatively explain behavioral data on human speech learning and derive predictions for future experiments.
Directory of Open Access Journals (Sweden)
Izzet B Yildiz
Full Text Available Our knowledge about the computational mechanisms underlying human learning and recognition of sound sequences, especially speech, is still very limited. One difficulty in deciphering the exact means by which humans recognize speech is that there are scarce experimental findings at a neuronal, microscopic level. Here, we show that our neuronal-computational understanding of speech learning and recognition may be vastly improved by looking at an animal model, i.e., the songbird, which faces the same challenge as humans: to learn and decode complex auditory input, in an online fashion. Motivated by striking similarities between the human and songbird neural recognition systems at the macroscopic level, we assumed that the human brain uses the same computational principles at a microscopic level and translated a birdsong model into a novel human sound learning and recognition model with an emphasis on speech. We show that the resulting Bayesian model with a hierarchy of nonlinear dynamical systems can learn speech samples such as words rapidly and recognize them robustly, even in adverse conditions. In addition, we show that recognition can be performed even when words are spoken by different speakers and with different accents-an everyday situation in which current state-of-the-art speech recognition models often fail. The model can also be used to qualitatively explain behavioral data on human speech learning and derive predictions for future experiments.
Akhtar, Naveed; Mian, Ajmal
2017-10-03
We present a principled approach to learn a discriminative dictionary along a linear classifier for hyperspectral classification. Our approach places Gaussian Process priors over the dictionary to account for the relative smoothness of the natural spectra, whereas the classifier parameters are sampled from multivariate Gaussians. We employ two Beta-Bernoulli processes to jointly infer the dictionary and the classifier. These processes are coupled under the same sets of Bernoulli distributions. In our approach, these distributions signify the frequency of the dictionary atom usage in representing class-specific training spectra, which also makes the dictionary discriminative. Due to the coupling between the dictionary and the classifier, the popularity of the atoms for representing different classes gets encoded into the classifier. This helps in predicting the class labels of test spectra that are first represented over the dictionary by solving a simultaneous sparse optimization problem. The labels of the spectra are predicted by feeding the resulting representations to the classifier. Our approach exploits the nonparametric Bayesian framework to automatically infer the dictionary size--the key parameter in discriminative dictionary learning. Moreover, it also has the desirable property of adaptively learning the association between the dictionary atoms and the class labels by itself. We use Gibbs sampling to infer the posterior probability distributions over the dictionary and the classifier under the proposed model, for which, we derive analytical expressions. To establish the effectiveness of our approach, we test it on benchmark hyperspectral images. The classification performance is compared with the state-of-the-art dictionary learning-based classification methods.
ACES-Based Testbed and Bayesian Game-Theoretic Framework for Dynamic Airspace Configuration, Phase I
National Aeronautics and Space Administration — The key innovation in this effort is the development of algorithms and a framework for automated Dynamic Airspace Configuration (DAC) using a cooperative Bayesian...
A Probability-based Evolutionary Algorithm with Mutations to Learn Bayesian Networks
Directory of Open Access Journals (Sweden)
Sho Fukuda
2014-12-01
Full Text Available Bayesian networks are regarded as one of the essential tools to analyze causal relationship between events from data. To learn the structure of highly-reliable Bayesian networks from data as quickly as possible is one of the important problems that several studies have been tried to achieve. In recent years, probability-based evolutionary algorithms have been proposed as a new efficient approach to learn Bayesian networks. In this paper, we target on one of the probability-based evolutionary algorithms called PBIL (Probability-Based Incremental Learning, and propose a new mutation operator. Through performance evaluation, we found that the proposed mutation operator has a good performance in learning Bayesian networks
Intention Recognition for Partial-Order Plans Using Dynamic Bayesian Networks
Krauthausen, Peter; Hanebeck, Uwe D.
2009-01-01
In this paper, a novel probabilistic approach to intention recognition for partial-order plans is proposed. The key idea is to exploit independences between subplans to substantially reduce the state space sizes in the compiled Dynamic Bayesian Networks. This makes inference more efficient. The main con- tributions are the computationally exploitable definition of subplan structures, the introduction of a novel Lay- ered Intention Model and a Dynamic Bayesian Net- work representation with an ...
Liu, Xun; Xue, Wei; Xiao, Lei; Zhang, Bo
2017-01-01
We describe a parallel bayesian online deep learning framework (PBODL) for click-through rate (CTR) prediction within today's Tencent advertising system, which provides quick and accurate learning of user preferences. We first explain the framework with a deep probit regression model, which is trained with probabilistic back-propagation in the mode of assumed Gaussian density filtering. Then we extend the model family to a variety of bayesian online models with increasing feature embedding ca...
Directory of Open Access Journals (Sweden)
Yue Zhao
2012-12-01
Full Text Available Audio-visual speech recognition is a natural and robust approach to improving human-robot interaction in noisy environments. Although multi-stream Dynamic Bayesian Network and coupled HMM are widely used for audio-visual speech recognition, they fail to learn the shared features between modalities and ignore the dependency of features among the frames within each discrete state. In this paper, we propose a Deep Dynamic Bayesian Network (DDBN to perform unsupervised extraction of spatial-temporal multimodal features from Tibetan audio-visual speech data and build an accurate audio-visual speech recognition model under a no frame-independency assumption. The experiment results on Tibetan speech data from some real-world environments showed the proposed DDBN outperforms the state-of-art methods in word recognition accuracy.
Robust Learning of High-dimensional Biological Networks with Bayesian Networks
Nägele, Andreas; Dejori, Mathäus; Stetter, Martin
Structure learning of Bayesian networks applied to gene expression data has become a potentially useful method to estimate interactions between genes. However, the NP-hardness of Bayesian network structure learning renders the reconstruction of the full genetic network with thousands of genes unfeasible. Consequently, the maximal network size is usually restricted dramatically to a small set of genes (corresponding with variables in the Bayesian network). Although this feature reduction step makes structure learning computationally tractable, on the downside, the learned structure might be adversely affected due to the introduction of missing genes. Additionally, gene expression data are usually very sparse with respect to the number of samples, i.e., the number of genes is much greater than the number of different observations. Given these problems, learning robust network features from microarray data is a challenging task. This chapter presents several approaches tackling the robustness issue in order to obtain a more reliable estimation of learned network features.
Reinforcement Learning Based on the Bayesian Theorem for Electricity Markets Decision Support
DEFF Research Database (Denmark)
Sousa, Tiago; Pinto, Tiago; Praca, Isabel
2014-01-01
This paper presents the applicability of a reinforcement learning algorithm based on the application of the Bayesian theorem of probability. The proposed reinforcement learning algorithm is an advantageous and indispensable tool for ALBidS (Adaptive Learning strategic Bidding System), a multi...
Distributed Diagnosis in Uncertain Environments Using Dynamic Bayesian Networks
National Aeronautics and Space Administration — This paper presents a distributed Bayesian fault diagnosis scheme for physical systems. Our diagnoser design is based on a procedure for factoring the global system...
Flexible Bayesian Dynamic Modeling of Covariance and Correlation Matrices
Lan, Shiwei; Holbrook, Andrew; Fortin, Norbert J.; Ombao, Hernando; Shahbaba, Babak
2017-01-01
Modeling covariance (and correlation) matrices is a challenging problem due to the large dimensionality and positive-definiteness constraint. In this paper, we propose a novel Bayesian framework based on decomposing the covariance matrix
Bayesian Inference for Functional Dynamics Exploring in fMRI Data
Directory of Open Access Journals (Sweden)
Xuan Guo
2016-01-01
Full Text Available This paper aims to review state-of-the-art Bayesian-inference-based methods applied to functional magnetic resonance imaging (fMRI data. Particularly, we focus on one specific long-standing challenge in the computational modeling of fMRI datasets: how to effectively explore typical functional interactions from fMRI time series and the corresponding boundaries of temporal segments. Bayesian inference is a method of statistical inference which has been shown to be a powerful tool to encode dependence relationships among the variables with uncertainty. Here we provide an introduction to a group of Bayesian-inference-based methods for fMRI data analysis, which were designed to detect magnitude or functional connectivity change points and to infer their functional interaction patterns based on corresponding temporal boundaries. We also provide a comparison of three popular Bayesian models, that is, Bayesian Magnitude Change Point Model (BMCPM, Bayesian Connectivity Change Point Model (BCCPM, and Dynamic Bayesian Variable Partition Model (DBVPM, and give a summary of their applications. We envision that more delicate Bayesian inference models will be emerging and play increasingly important roles in modeling brain functions in the years to come.
Risk, unexpected uncertainty, and estimation uncertainty: Bayesian learning in unstable settings.
Directory of Open Access Journals (Sweden)
Elise Payzan-LeNestour
Full Text Available Recently, evidence has emerged that humans approach learning using Bayesian updating rather than (model-free reinforcement algorithms in a six-arm restless bandit problem. Here, we investigate what this implies for human appreciation of uncertainty. In our task, a Bayesian learner distinguishes three equally salient levels of uncertainty. First, the Bayesian perceives irreducible uncertainty or risk: even knowing the payoff probabilities of a given arm, the outcome remains uncertain. Second, there is (parameter estimation uncertainty or ambiguity: payoff probabilities are unknown and need to be estimated. Third, the outcome probabilities of the arms change: the sudden jumps are referred to as unexpected uncertainty. We document how the three levels of uncertainty evolved during the course of our experiment and how it affected the learning rate. We then zoom in on estimation uncertainty, which has been suggested to be a driving force in exploration, in spite of evidence of widespread aversion to ambiguity. Our data corroborate the latter. We discuss neural evidence that foreshadowed the ability of humans to distinguish between the three levels of uncertainty. Finally, we investigate the boundaries of human capacity to implement Bayesian learning. We repeat the experiment with different instructions, reflecting varying levels of structural uncertainty. Under this fourth notion of uncertainty, choices were no better explained by Bayesian updating than by (model-free reinforcement learning. Exit questionnaires revealed that participants remained unaware of the presence of unexpected uncertainty and failed to acquire the right model with which to implement Bayesian updating.
Bayes Academy - An Educational Game for Learning Bayesian Networks
Sotala, Kaj
2015-01-01
This thesis describes the development of 'Bayes Academy', an educational game which aims to teach an understanding of Bayesian networks. A Bayesian network is a directed acyclic graph describing a joint probability distribution function over n random variables, where each node in the graph represents a random variable. To find a way to turn this subject into an interesting game, this work draws on the theoretical background of meaningful play. Among other requirements, actions in the game...
Reconstructing Constructivism: Causal Models, Bayesian Learning Mechanisms, and the Theory Theory
Gopnik, Alison; Wellman, Henry M.
2012-01-01
We propose a new version of the "theory theory" grounded in the computational framework of probabilistic causal models and Bayesian learning. Probabilistic models allow a constructivist but rigorous and detailed approach to cognitive development. They also explain the learning of both more specific causal hypotheses and more abstract framework…
A Bayesian Panel Data Approach to Explaining Market Beta Dynamics
R. Bauer (Rob); M.M.J.E. Cosemans (Mathijs); R. Frehen (Rik); P.C. Schotman (Peter)
2008-01-01
markdownabstractWe characterize the process that drives the market betas of individual stocks by setting up a hierarchical Bayesian panel data model that allows a flexible specification for beta. We show that combining the parametric relationship between betas and conditioning variables specified by
Gerven, M.A.J. van
2007-01-01
This dissertation deals with decision support in the context of clinical oncology. (Dynamic) Bayesian networks are used as a framework for (dynamic) decision-making under uncertainty and applied to a variety of diagnostic, prognostic, and treatment problems in medicine. It is shown that the proposed
Directory of Open Access Journals (Sweden)
Akira Taniguchi
2017-12-01
Full Text Available In this paper, we propose a Bayesian generative model that can form multiple categories based on each sensory-channel and can associate words with any of the four sensory-channels (action, position, object, and color. This paper focuses on cross-situational learning using the co-occurrence between words and information of sensory-channels in complex situations rather than conventional situations of cross-situational learning. We conducted a learning scenario using a simulator and a real humanoid iCub robot. In the scenario, a human tutor provided a sentence that describes an object of visual attention and an accompanying action to the robot. The scenario was set as follows: the number of words per sensory-channel was three or four, and the number of trials for learning was 20 and 40 for the simulator and 25 and 40 for the real robot. The experimental results showed that the proposed method was able to estimate the multiple categorizations and to learn the relationships between multiple sensory-channels and words accurately. In addition, we conducted an action generation task and an action description task based on word meanings learned in the cross-situational learning scenario. The experimental results showed that the robot could successfully use the word meanings learned by using the proposed method.
Testing students' e-learning via Facebook through Bayesian structural equation modeling.
Salarzadeh Jenatabadi, Hashem; Moghavvemi, Sedigheh; Wan Mohamed Radzi, Che Wan Jasimah Bt; Babashamsi, Parastoo; Arashi, Mohammad
2017-01-01
Learning is an intentional activity, with several factors affecting students' intention to use new learning technology. Researchers have investigated technology acceptance in different contexts by developing various theories/models and testing them by a number of means. Although most theories/models developed have been examined through regression or structural equation modeling, Bayesian analysis offers more accurate data analysis results. To address this gap, the unified theory of acceptance and technology use in the context of e-learning via Facebook are re-examined in this study using Bayesian analysis. The data (S1 Data) were collected from 170 students enrolled in a business statistics course at University of Malaya, Malaysia, and tested with the maximum likelihood and Bayesian approaches. The difference between the two methods' results indicates that performance expectancy and hedonic motivation are the strongest factors influencing the intention to use e-learning via Facebook. The Bayesian estimation model exhibited better data fit than the maximum likelihood estimator model. The results of the Bayesian and maximum likelihood estimator approaches are compared and the reasons for the result discrepancy are deliberated.
Testing students' e-learning via Facebook through Bayesian structural equation modeling.
Directory of Open Access Journals (Sweden)
Hashem Salarzadeh Jenatabadi
Full Text Available Learning is an intentional activity, with several factors affecting students' intention to use new learning technology. Researchers have investigated technology acceptance in different contexts by developing various theories/models and testing them by a number of means. Although most theories/models developed have been examined through regression or structural equation modeling, Bayesian analysis offers more accurate data analysis results. To address this gap, the unified theory of acceptance and technology use in the context of e-learning via Facebook are re-examined in this study using Bayesian analysis. The data (S1 Data were collected from 170 students enrolled in a business statistics course at University of Malaya, Malaysia, and tested with the maximum likelihood and Bayesian approaches. The difference between the two methods' results indicates that performance expectancy and hedonic motivation are the strongest factors influencing the intention to use e-learning via Facebook. The Bayesian estimation model exhibited better data fit than the maximum likelihood estimator model. The results of the Bayesian and maximum likelihood estimator approaches are compared and the reasons for the result discrepancy are deliberated.
Multinomial Bayesian learning for modeling classical and nonclassical receptive field properties.
Hosoya, Haruo
2012-08-01
We study the interplay of Bayesian inference and natural image learning in a hierarchical vision system, in relation to the response properties of early visual cortex. We particularly focus on a Bayesian network with multinomial variables that can represent discrete feature spaces similar to hypercolumns combining minicolumns, enforce sparsity of activation to learn efficient representations, and explain divisive normalization. We demonstrate that maximal-likelihood learning using sampling-based Bayesian inference gives rise to classical receptive field properties similar to V1 simple cells and V2 cells, while inference performed on the trained network yields nonclassical context-dependent response properties such as cross-orientation suppression and filling in. Comparison with known physiological properties reveals some qualitative and quantitative similarities.
Inventory model using bayesian dynamic linear model for demand forecasting
Directory of Open Access Journals (Sweden)
Marisol Valencia-Cárdenas
2014-12-01
Full Text Available An important factor of manufacturing process is the inventory management of terminated product. Constantly, industry is looking for better alternatives to establish an adequate plan of production and stored quantities, with optimal cost, getting quantities in a time horizon, which permits to define resources and logistics with anticipation, needed to distribute products on time. Total absence of historical data, required by many statistical models to forecast, demands the search for other kind of accurate techniques. This work presents an alternative that not only permits to forecast, in an adjusted way, but also, to provide optimal quantities to produce and store with an optimal cost, using Bayesian statistics. The proposal is illustrated with real data. Palabras clave: estadística bayesiana, optimización, modelo de inventarios, modelo lineal dinámico bayesiano. Keywords: Bayesian statistics, opti
Education tools for dynamic Bayesian decision-making
Czech Academy of Sciences Publication Activity Database
Suzdaleva, Evgenia; Nedoma, Petr
2006-01-01
Roč. 5, č. 3 (2006), s. 288-295 ISSN 1790-1979 R&D Projects: GA ČR GP201/06/P434; GA ČR GA102/03/0049 Institutional research plan: CEZ:AV0Z10750506 Keywords : educational system * Bayesian decision-making * probabilistic mixtures Subject RIV: JC - Computer Hardware ; Software http://library.utia.cas.cz/prace/20060144.pdf
Technical note: Bayesian calibration of dynamic ruminant nutrition models.
Reed, K F; Arhonditsis, G B; France, J; Kebreab, E
2016-08-01
Mechanistic models of ruminant digestion and metabolism have advanced our understanding of the processes underlying ruminant animal physiology. Deterministic modeling practices ignore the inherent variation within and among individual animals and thus have no way to assess how sources of error influence model outputs. We introduce Bayesian calibration of mathematical models to address the need for robust mechanistic modeling tools that can accommodate error analysis by remaining within the bounds of data-based parameter estimation. For the purpose of prediction, the Bayesian approach generates a posterior predictive distribution that represents the current estimate of the value of the response variable, taking into account both the uncertainty about the parameters and model residual variability. Predictions are expressed as probability distributions, thereby conveying significantly more information than point estimates in regard to uncertainty. Our study illustrates some of the technical advantages of Bayesian calibration and discusses the future perspectives in the context of animal nutrition modeling. Copyright © 2016 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.
Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis
Directory of Open Access Journals (Sweden)
Chernoded Andrey
2017-01-01
Full Text Available Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.
A dynamic discretization method for reliability inference in Dynamic Bayesian Networks
International Nuclear Information System (INIS)
Zhu, Jiandao; Collette, Matthew
2015-01-01
The material and modeling parameters that drive structural reliability analysis for marine structures are subject to a significant uncertainty. This is especially true when time-dependent degradation mechanisms such as structural fatigue cracking are considered. Through inspection and monitoring, information such as crack location and size can be obtained to improve these parameters and the corresponding reliability estimates. Dynamic Bayesian Networks (DBNs) are a powerful and flexible tool to model dynamic system behavior and update reliability and uncertainty analysis with life cycle data for problems such as fatigue cracking. However, a central challenge in using DBNs is the need to discretize certain types of continuous random variables to perform network inference while still accurately tracking low-probability failure events. Most existing discretization methods focus on getting the overall shape of the distribution correct, with less emphasis on the tail region. Therefore, a novel scheme is presented specifically to estimate the likelihood of low-probability failure events. The scheme is an iterative algorithm which dynamically partitions the discretization intervals at each iteration. Through applications to two stochastic crack-growth example problems, the algorithm is shown to be robust and accurate. Comparisons are presented between the proposed approach and existing methods for the discretization problem. - Highlights: • A dynamic discretization method is developed for low-probability events in DBNs. • The method is compared to existing approaches on two crack growth problems. • The method is shown to improve on existing methods for low-probability events
A Bayesian perspective on Markovian dynamics and the fluctuation theorem
Virgo, Nathaniel
2013-08-01
One of E. T. Jaynes' most important achievements was to derive statistical mechanics from the maximum entropy (MaxEnt) method. I re-examine a relatively new result in statistical mechanics, the Evans-Searles fluctuation theorem, from a MaxEnt perspective. This is done in the belief that interpreting such results in Bayesian terms will lead to new advances in statistical physics. The version of the fluctuation theorem that I will discuss applies to discrete, stochastic systems that begin in a non-equilibrium state and relax toward equilibrium. I will show that for such systems the fluctuation theorem can be seen as a consequence of the fact that the equilibrium distribution must obey the property of detailed balance. Although the principle of detailed balance applies only to equilibrium ensembles, it puts constraints on the form of non-equilibrium trajectories. This will be made clear by taking a novel kind of Bayesian perspective, in which the equilibrium distribution is seen as a prior over the system's set of possible trajectories. Non-equilibrium ensembles are calculated from this prior using Bayes' theorem, with the initial conditions playing the role of the data. I will also comment on the implications of this perspective for the question of how to derive the second law.
Bayesian interpolation in a dynamic sinusoidal model with application to packet-loss concealment
DEFF Research Database (Denmark)
Nielsen, Jesper Kjær; Christensen, Mads Græsbøll; Cemgil, Ali Taylan
2010-01-01
a Bayesian inference scheme for the missing observations, hidden states and model parameters of the dynamic model. The inference scheme is based on a Markov chain Monte Carlo method known as Gibbs sampler. We illustrate the performance of the inference scheme to the application of packet-loss concealment...
A comparison of machine learning and Bayesian modelling for molecular serotyping.
Newton, Richard; Wernisch, Lorenz
2017-08-11
Streptococcus pneumoniae is a human pathogen that is a major cause of infant mortality. Identifying the pneumococcal serotype is an important step in monitoring the impact of vaccines used to protect against disease. Genomic microarrays provide an effective method for molecular serotyping. Previously we developed an empirical Bayesian model for the classification of serotypes from a molecular serotyping array. With only few samples available, a model driven approach was the only option. In the meanwhile, several thousand samples have been made available to us, providing an opportunity to investigate serotype classification by machine learning methods, which could complement the Bayesian model. We compare the performance of the original Bayesian model with two machine learning algorithms: Gradient Boosting Machines and Random Forests. We present our results as an example of a generic strategy whereby a preliminary probabilistic model is complemented or replaced by a machine learning classifier once enough data are available. Despite the availability of thousands of serotyping arrays, a problem encountered when applying machine learning methods is the lack of training data containing mixtures of serotypes; due to the large number of possible combinations. Most of the available training data comprises samples with only a single serotype. To overcome the lack of training data we implemented an iterative analysis, creating artificial training data of serotype mixtures by combining raw data from single serotype arrays. With the enhanced training set the machine learning algorithms out perform the original Bayesian model. However, for serotypes currently lacking sufficient training data the best performing implementation was a combination of the results of the Bayesian Model and the Gradient Boosting Machine. As well as being an effective method for classifying biological data, machine learning can also be used as an efficient method for revealing subtle biological
A novel Bayesian learning method for information aggregation in modular neural networks
DEFF Research Database (Denmark)
Wang, Pan; Xu, Lida; Zhou, Shang-Ming
2010-01-01
Modular neural network is a popular neural network model which has many successful applications. In this paper, a sequential Bayesian learning (SBL) is proposed for modular neural networks aiming at efficiently aggregating the outputs of members of the ensemble. The experimental results on eight...... benchmark problems have demonstrated that the proposed method can perform information aggregation efficiently in data modeling....
Best Response Bayesian Reinforcement Learning for Multiagent Systems with State Uncertainty
Oliehoek, F.A.; Amato, C.
2014-01-01
It is often assumed that agents in multiagent systems with state uncertainty have full knowledge of the model of dy- namics and sensors, but in many cases this is not feasible. A more realistic assumption is that agents must learn about the environment and other agents while acting. Bayesian methods
Low Complexity Sparse Bayesian Learning for Channel Estimation Using Generalized Mean Field
DEFF Research Database (Denmark)
Pedersen, Niels Lovmand; Manchón, Carles Navarro; Fleury, Bernard Henri
2014-01-01
We derive low complexity versions of a wide range of algorithms for sparse Bayesian learning (SBL) in underdetermined linear systems. The proposed algorithms are obtained by applying the generalized mean field (GMF) inference framework to a generic SBL probabilistic model. In the GMF framework, we...
A Dynamic Bayesian Network Model for the Production and Inventory Control
Shin, Ji-Sun; Takazaki, Noriyuki; Lee, Tae-Hong; Kim, Jin-Il; Lee, Hee-Hyol
In general, the production quantities and delivered goods are changed randomly and then the total stock is also changed randomly. This paper deals with the production and inventory control using the Dynamic Bayesian Network. Bayesian Network is a probabilistic model which represents the qualitative dependence between two or more random variables by the graph structure, and indicates the quantitative relations between individual variables by the conditional probability. The probabilistic distribution of the total stock is calculated through the propagation of the probability on the network. Moreover, an adjusting rule of the production quantities to maintain the probability of a lower limit and a ceiling of the total stock to certain values is shown.
Bayesian estimation of mixtures with dynamic transitions and known component parameters
Czech Academy of Sciences Publication Activity Database
Nagy, I.; Suzdaleva, Evgenia; Kárný, Miroslav
2011-01-01
Roč. 47, č. 4 (2011), s. 572-594 ISSN 0023-5954 R&D Projects: GA MŠk 1M0572; GA TA ČR TA01030123; GA ČR GA102/08/0567 Grant - others:Skoda Auto(CZ) ENS/2009/UTIA Institutional research plan: CEZ:AV0Z10750506 Keywords : mixture model * Bayesian estimation * approximation * clustering * classification Subject RIV: BC - Control Systems Theory Impact factor: 0.454, year: 2011 http://library.utia.cas.cz/separaty/2011/AS/nagy-bayesian estimation of mixtures with dynamic transitions and known component parameters.pdf
Learning the Structure of Bayesian Network from Small Amount of Data
Directory of Open Access Journals (Sweden)
Bogdan COCU
2009-12-01
Full Text Available Many areas of artificial intelligence must handling with imperfection ofinformation. One of the ways to do this is using representation and reasoning withBayesian networks. Creation of a Bayesian network consists in two stages. First stage isto design the node structure and directed links between them. Choosing of a structurefor network can be done either through empirical developing by human experts orthrough machine learning algorithm. The second stage is completion of probabilitytables for each node. Using a machine learning method is useful, especially when wehave a big amount of leaning data. But in many fields the amount of data is small,incomplete and inconsistent. In this paper, we make a case study for choosing the bestlearning method for small amount of learning data. Means more experiments we dropconclusion of using existent methods for learning a network structure.
Bayesian Learning and the Regulation of Greenhouse Gas Emissions
Karp, Larry; Zhang, Jiangfeng
2001-01-01
We study the importance of anticipated learning - about both environmental damages and abatement costs - in determining the level and the method of controlling greenhouse gas emissions. We also compare active learning, passive learning, and parameter uncertainty without learning. Current beliefs about damages and abatement costs have an important effect on the optimal level of emissions, However, the optimal level of emissions is not sensitive either to the possibility of learning about damag...
Reconstructing constructivism: Causal models, Bayesian learning mechanisms and the theory theory
Gopnik, Alison; Wellman, Henry M.
2012-01-01
We propose a new version of the “theory theory” grounded in the computational framework of probabilistic causal models and Bayesian learning. Probabilistic models allow a constructivist but rigorous and detailed approach to cognitive development. They also explain the learning of both more specific causal hypotheses and more abstract framework theories. We outline the new theoretical ideas, explain the computational framework in an intuitive and non-technical way, and review an extensive but ...
OFDM receiver for fast time-varying channels using block-sparse Bayesian learning
DEFF Research Database (Denmark)
Barbu, Oana-Elena; Manchón, Carles Navarro; Rom, Christian
2016-01-01
characterized with a basis expansion model using a small number of terms. As a result, the channel estimation problem is posed as that of estimating a vector of complex coefficients that exhibits a block-sparse structure, which we solve with tools from block-sparse Bayesian learning. Using variational Bayesian...... inference, we embed the channel estimator in a receiver structure that performs iterative channel and noise precision estimation, intercarrier interference cancellation, detection and decoding. Simulation results illustrate the superior performance of the proposed receiver over state-of-art receivers....
Using literature and data to learn Bayesian networks as clinical models of ovarian tumors
DEFF Research Database (Denmark)
Antal, P.; Fannes, G.; Timmerman, D.
2004-01-01
Thanks to its increasing availability, electronic literature has become a potential source of information for the development of complex Bayesian networks (BN), when human expertise is missing or data is scarce or contains much noise. This opportunity raises the question of how to integrate...... information from free-text resources with statistical data in learning Bayesian networks. Firstly, we report on the collection of prior information resources in the ovarian cancer domain, which includes "kernel" annotations of the domain variables. We introduce methods based on the annotations and literature...
Directory of Open Access Journals (Sweden)
Ming Li
2018-06-01
Full Text Available The effective prediction of storm track (ST is greatly beneficial for analyzing the development and anomalies of mid-latitude weather systems. For the non-stationarity, nonlinearity, and uncertainty of ST intensity index (STII, a new probabilistic prediction model was proposed based on dynamic Bayesian network (DBN and wavelet analysis (WA. We introduced probability theory and graph theory for the first time to quantitatively describe the nonlinear relationship and uncertain interaction of the ST system. Then a casual prediction network (i.e., DBN was constructed through wavelet decomposition, structural learning, parameter learning, and probabilistic inference, which was used for expression of relation among predictors and probabilistic prediction of STII. The intensity prediction of the North Pacific ST with data from 1961–2010 showed that the new model was able to give more comprehensive prediction information and higher prediction accuracy and had strong generalization ability and good stability.
Supervised Learning for Dynamical System Learning.
Hefny, Ahmed; Downey, Carlton; Gordon, Geoffrey J
2015-01-01
Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoff between computational and statistical efficiency. Unfortunately, they can be difficult to use and extend in practice: e.g., they can make it difficult to incorporate prior information such as sparsity or structure. To address this problem, we present a new view of dynamical system learning: we show how to learn dynamical systems by solving a sequence of ordinary supervised learning problems, thereby allowing users to incorporate prior knowledge via standard techniques such as L 1 regularization. Many existing spectral methods are special cases of this new framework, using linear regression as the supervised learner. We demonstrate the effectiveness of our framework by showing examples where nonlinear regression or lasso let us learn better state representations than plain linear regression does; the correctness of these instances follows directly from our general analysis.
Bayesian state space models for dynamic genetic network construction across multiple tissues.
Liang, Yulan; Kelemen, Arpad
2016-08-01
Construction of gene-gene interaction networks and potential pathways is a challenging and important problem in genomic research for complex diseases while estimating the dynamic changes of the temporal correlations and non-stationarity are the keys in this process. In this paper, we develop dynamic state space models with hierarchical Bayesian settings to tackle this challenge for inferring the dynamic profiles and genetic networks associated with disease treatments. We treat both the stochastic transition matrix and the observation matrix time-variant and include temporal correlation structures in the covariance matrix estimations in the multivariate Bayesian state space models. The unevenly spaced short time courses with unseen time points are treated as hidden state variables. Hierarchical Bayesian approaches with various prior and hyper-prior models with Monte Carlo Markov Chain and Gibbs sampling algorithms are used to estimate the model parameters and the hidden state variables. We apply the proposed Hierarchical Bayesian state space models to multiple tissues (liver, skeletal muscle, and kidney) Affymetrix time course data sets following corticosteroid (CS) drug administration. Both simulation and real data analysis results show that the genomic changes over time and gene-gene interaction in response to CS treatment can be well captured by the proposed models. The proposed dynamic Hierarchical Bayesian state space modeling approaches could be expanded and applied to other large scale genomic data, such as next generation sequence (NGS) combined with real time and time varying electronic health record (EHR) for more comprehensive and robust systematic and network based analysis in order to transform big biomedical data into predictions and diagnostics for precision medicine and personalized healthcare with better decision making and patient outcomes.
Tsionas, Mike G.; Michaelides, Panayotis G.
2017-09-01
We use a novel Bayesian inference procedure for the Lyapunov exponent in the dynamical system of returns and their unobserved volatility. In the dynamical system, computation of largest Lyapunov exponent by traditional methods is impossible as the stochastic nature has to be taken explicitly into account due to unobserved volatility. We apply the new techniques to daily stock return data for a group of six countries, namely USA, UK, Switzerland, Netherlands, Germany and France, from 2003 to 2014, by means of Sequential Monte Carlo for Bayesian inference. The evidence points to the direction that there is indeed noisy chaos both before and after the recent financial crisis. However, when a much simpler model is examined where the interaction between returns and volatility is not taken into consideration jointly, the hypothesis of chaotic dynamics does not receive much support by the data ("neglected chaos").
Upper-Lower Bounds Candidate Sets Searching Algorithm for Bayesian Network Structure Learning
Directory of Open Access Journals (Sweden)
Guangyi Liu
2014-01-01
Full Text Available Bayesian network is an important theoretical model in artificial intelligence field and also a powerful tool for processing uncertainty issues. Considering the slow convergence speed of current Bayesian network structure learning algorithms, a fast hybrid learning method is proposed in this paper. We start with further analysis of information provided by low-order conditional independence testing, and then two methods are given for constructing graph model of network, which is theoretically proved to be upper and lower bounds of the structure space of target network, so that candidate sets are given as a result; after that a search and scoring algorithm is operated based on the candidate sets to find the final structure of the network. Simulation results show that the algorithm proposed in this paper is more efficient than similar algorithms with the same learning precision.
Using literature and data to learn Bayesian networks as clinical models of ovarian tumors.
Antal, Peter; Fannes, Geert; Timmerman, Dirk; Moreau, Yves; De Moor, Bart
2004-03-01
Thanks to its increasing availability, electronic literature has become a potential source of information for the development of complex Bayesian networks (BN), when human expertise is missing or data is scarce or contains much noise. This opportunity raises the question of how to integrate information from free-text resources with statistical data in learning Bayesian networks. Firstly, we report on the collection of prior information resources in the ovarian cancer domain, which includes "kernel" annotations of the domain variables. We introduce methods based on the annotations and literature to derive informative pairwise dependency measures, which are derived from the statistical cooccurrence of the names of the variables, from the similarity of the "kernel" descriptions of the variables and from a combined method. We perform wide-scale evaluation of these text-based dependency scores against an expert reference and against data scores (the mutual information (MI) and a Bayesian score). Next, we transform the text-based dependency measures into informative text-based priors for Bayesian network structures. Finally, we report the benefit of such informative text-based priors on the performance of a Bayesian network for the classification of ovarian tumors from clinical data.
Bayesian estimation of dynamic matching function for U-V analysis in Japan
Kyo, Koki; Noda, Hideo; Kitagawa, Genshiro
2012-05-01
In this paper we propose a Bayesian method for analyzing unemployment dynamics. We derive a Beveridge curve for unemployment and vacancy (U-V) analysis from a Bayesian model based on a labor market matching function. In our framework, the efficiency of matching and the elasticities of new hiring with respect to unemployment and vacancy are regarded as time varying parameters. To construct a flexible model and obtain reasonable estimates in an underdetermined estimation problem, we treat the time varying parameters as random variables and introduce smoothness priors. The model is then described in a state space representation, enabling the parameter estimation to be carried out using Kalman filter and fixed interval smoothing. In such a representation, dynamic features of the cyclic unemployment rate and the structural-frictional unemployment rate can be accurately captured.
Non-parametric Bayesian models of response function in dynamic image sequences
Czech Academy of Sciences Publication Activity Database
Tichý, Ondřej; Šmídl, Václav
2016-01-01
Roč. 151, č. 1 (2016), s. 90-100 ISSN 1077-3142 R&D Projects: GA ČR GA13-29225S Institutional support: RVO:67985556 Keywords : Response function * Blind source separation * Dynamic medical imaging * Probabilistic models * Bayesian methods Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.498, year: 2016 http://library.utia.cas.cz/separaty/2016/AS/tichy-0456983.pdf
International Nuclear Information System (INIS)
Peng, Weiwen; Li, Yan-Feng; Mi, Jinhua; Yu, Le; Huang, Hong-Zhong
2016-01-01
Degradation analysis is critical to reliability assessment and operational management of complex systems. Two types of assumptions are often adopted for degradation analysis: (1) single degradation indicator and (2) constant external factors. However, modern complex systems are generally characterized as multiple functional and suffered from multiple failure modes due to dynamic operating conditions. In this paper, Bayesian degradation analysis of complex systems with multiple degradation indicators under dynamic conditions is investigated. Three practical engineering-driven issues are addressed: (1) to model various combinations of degradation indicators, a generalized multivariate hybrid degradation process model is proposed, which subsumes both monotonic and non-monotonic degradation processes models as special cases, (2) to study effects of external factors, two types of dynamic covariates are incorporated jointly, which include both environmental conditions and operating profiles, and (3) to facilitate degradation based reliability analysis, a serial of Bayesian strategy is constructed, which covers parameter estimation, factor-related degradation prediction, and unit-specific remaining useful life assessment. Finally, degradation analysis of a type of heavy machine tools is presented to demonstrate the application and performance of the proposed method. A comparison of the proposed model with a traditional model is studied as well in the example. - Highlights: • A generalized multivariate hybrid degradation process model is introduced. • Various types of dependent degradation processes can be modeled coherently. • The effects of environmental conditions and operating profiles are investigated. • Unit-specific RUL assessment is implemented through a two-step Bayesian method.
Adaptive learning and complex dynamics
International Nuclear Information System (INIS)
Gomes, Orlando
2009-01-01
In this paper, we explore the dynamic properties of a group of simple deterministic difference equation systems in which the conventional perfect foresight assumption gives place to a mechanism of adaptive learning. These systems have a common feature: under perfect foresight (or rational expectations) they all possess a unique fixed point steady state. This long-term outcome is obtained also under learning if the quality underlying the learning process is high. Otherwise, when the degree of inefficiency of the learning process is relatively strong, nonlinear dynamics (periodic and a-periodic cycles) arise. The specific properties of each one of the proposed systems is explored both in terms of local and global dynamics. One macroeconomic model is used to illustrate how the formation of expectations through learning may eventually lead to awkward long-term outcomes.
Learning Bayesian network structure: towards the essential graph by integer linear programming tools
Czech Academy of Sciences Publication Activity Database
Studený, Milan; Haws, D.
2014-01-01
Roč. 55, č. 4 (2014), s. 1043-1071 ISSN 0888-613X R&D Projects: GA ČR GA13-20012S Institutional support: RVO:67985556 Keywords : learning Bayesian network structure * integer linear programming * characteristic imset * essential graph Subject RIV: BA - General Mathematics Impact factor: 2.451, year: 2014 http://library.utia.cas.cz/separaty/2014/MTR/studeny-0427002.pdf
A Bayesian framework for parameter estimation in dynamical models.
Directory of Open Access Journals (Sweden)
Flávio Codeço Coelho
Full Text Available Mathematical models in biology are powerful tools for the study and exploration of complex dynamics. Nevertheless, bringing theoretical results to an agreement with experimental observations involves acknowledging a great deal of uncertainty intrinsic to our theoretical representation of a real system. Proper handling of such uncertainties is key to the successful usage of models to predict experimental or field observations. This problem has been addressed over the years by many tools for model calibration and parameter estimation. In this article we present a general framework for uncertainty analysis and parameter estimation that is designed to handle uncertainties associated with the modeling of dynamic biological systems while remaining agnostic as to the type of model used. We apply the framework to fit an SIR-like influenza transmission model to 7 years of incidence data in three European countries: Belgium, the Netherlands and Portugal.
Occam factors and model independent Bayesian learning of continuous distributions
International Nuclear Information System (INIS)
Nemenman, Ilya; Bialek, William
2002-01-01
Learning of a smooth but nonparametric probability density can be regularized using methods of quantum field theory. We implement a field theoretic prior numerically, test its efficacy, and show that the data and the phase space factors arising from the integration over the model space determine the free parameter of the theory ('smoothness scale') self-consistently. This persists even for distributions that are atypical in the prior and is a step towards a model independent theory for learning continuous distributions. Finally, we point out that a wrong parametrization of a model family may sometimes be advantageous for small data sets
A Bayesian method for construction of Markov models to describe dynamics on various time-scales.
Rains, Emily K; Andersen, Hans C
2010-10-14
The dynamics of many biological processes of interest, such as the folding of a protein, are slow and complicated enough that a single molecular dynamics simulation trajectory of the entire process is difficult to obtain in any reasonable amount of time. Moreover, one such simulation may not be sufficient to develop an understanding of the mechanism of the process, and multiple simulations may be necessary. One approach to circumvent this computational barrier is the use of Markov state models. These models are useful because they can be constructed using data from a large number of shorter simulations instead of a single long simulation. This paper presents a new Bayesian method for the construction of Markov models from simulation data. A Markov model is specified by (τ,P,T), where τ is the mesoscopic time step, P is a partition of configuration space into mesostates, and T is an N(P)×N(P) transition rate matrix for transitions between the mesostates in one mesoscopic time step, where N(P) is the number of mesostates in P. The method presented here is different from previous Bayesian methods in several ways. (1) The method uses Bayesian analysis to determine the partition as well as the transition probabilities. (2) The method allows the construction of a Markov model for any chosen mesoscopic time-scale τ. (3) It constructs Markov models for which the diagonal elements of T are all equal to or greater than 0.5. Such a model will be called a "consistent mesoscopic Markov model" (CMMM). Such models have important advantages for providing an understanding of the dynamics on a mesoscopic time-scale. The Bayesian method uses simulation data to find a posterior probability distribution for (P,T) for any chosen τ. This distribution can be regarded as the Bayesian probability that the kinetics observed in the atomistic simulation data on the mesoscopic time-scale τ was generated by the CMMM specified by (P,T). An optimization algorithm is used to find the most
Genome-wide prediction of discrete traits using bayesian regressions and machine learning
Directory of Open Access Journals (Sweden)
Forni Selma
2011-02-01
Full Text Available Abstract Background Genomic selection has gained much attention and the main goal is to increase the predictive accuracy and the genetic gain in livestock using dense marker information. Most methods dealing with the large p (number of covariates small n (number of observations problem have dealt only with continuous traits, but there are many important traits in livestock that are recorded in a discrete fashion (e.g. pregnancy outcome, disease resistance. It is necessary to evaluate alternatives to analyze discrete traits in a genome-wide prediction context. Methods This study shows two threshold versions of Bayesian regressions (Bayes A and Bayesian LASSO and two machine learning algorithms (boosting and random forest to analyze discrete traits in a genome-wide prediction context. These methods were evaluated using simulated and field data to predict yet-to-be observed records. Performances were compared based on the models' predictive ability. Results The simulation showed that machine learning had some advantages over Bayesian regressions when a small number of QTL regulated the trait under pure additivity. However, differences were small and disappeared with a large number of QTL. Bayesian threshold LASSO and boosting achieved the highest accuracies, whereas Random Forest presented the highest classification performance. Random Forest was the most consistent method in detecting resistant and susceptible animals, phi correlation was up to 81% greater than Bayesian regressions. Random Forest outperformed other methods in correctly classifying resistant and susceptible animals in the two pure swine lines evaluated. Boosting and Bayes A were more accurate with crossbred data. Conclusions The results of this study suggest that the best method for genome-wide prediction may depend on the genetic basis of the population analyzed. All methods were less accurate at correctly classifying intermediate animals than extreme animals. Among the different
Directory of Open Access Journals (Sweden)
David Lunn
Full Text Available The advantages of Bayesian statistical approaches, such as flexibility and the ability to acknowledge uncertainty in all parameters, have made them the prevailing method for analysing the spread of infectious diseases in human or animal populations. We introduce a Bayesian approach to experimental host-pathogen systems that shares these attractive features. Since uncertainty in all parameters is acknowledged, existing information can be accounted for through prior distributions, rather than through fixing some parameter values. The non-linear dynamics, multi-factorial design, multiple measurements of responses over time and sampling error that are typical features of experimental host-pathogen systems can also be naturally incorporated. We analyse the dynamics of the free-living protozoan Paramecium caudatum and its specialist bacterial parasite Holospora undulata. Our analysis provides strong evidence for a saturable infection function, and we were able to reproduce the two waves of infection apparent in the data by separating the initial inoculum from the parasites released after the first cycle of infection. In addition, the parameter estimates from the hierarchical model can be combined to infer variations in the parasite's basic reproductive ratio across experimental groups, enabling us to make predictions about the effect of resources and host genotype on the ability of the parasite to spread. Even though the high level of variability between replicates limited the resolution of the results, this Bayesian framework has strong potential to be used more widely in experimental ecology.
Energy Technology Data Exchange (ETDEWEB)
Brown, Justin [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Hund, Lauren [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
2017-02-01
Dynamic compression experiments are being performed on complicated materials using increasingly complex drivers. The data produced in these experiments are beginning to reach a regime where traditional analysis techniques break down; requiring the solution of an inverse problem. A common measurement in dynamic experiments is an interface velocity as a function of time, and often this functional output can be simulated using a hydrodynamics code. Bayesian model calibration is a statistical framework to estimate inputs into a computational model in the presence of multiple uncertainties, making it well suited to measurements of this type. In this article, we apply Bayesian model calibration to high pressure (250 GPa) ramp compression measurements in tantalum. We address several issues speci c to this calibration including the functional nature of the output as well as parameter and model discrepancy identi ability. Speci cally, we propose scaling the likelihood function by an e ective sample size rather than modeling the autocorrelation function to accommodate the functional output and propose sensitivity analyses using the notion of `modularization' to assess the impact of experiment-speci c nuisance input parameters on estimates of material properties. We conclude that the proposed Bayesian model calibration procedure results in simple, fast, and valid inferences on the equation of state parameters for tantalum.
Bayesian Modeling for Identification and Estimation of the Learning Effects of Pointing Tasks
Kyo, Koki
Recently, in the field of human-computer interaction, a model containing the systematic factor and human factor has been proposed to evaluate the performance of the input devices of a computer. This is called the SH-model. In this paper, in order to extend the range of application of the SH-model, we propose some new models based on the Box-Cox transformation and apply a Bayesian modeling method for identification and estimation of the learning effects of pointing tasks. We consider the parameters describing the learning effect as random variables and introduce smoothness priors for them. Illustrative results show that the newly-proposed models work well.
Structure Learning of Linear Bayesian Networks in High-Dimensions
Aragam, Nikhyl Bryon
2015-01-01
Research into graphical models is a rapidly developing enterprise, garnering significant interest from both the statistics and machine learning communities. A parallel thread in both communities has been the study of low-dimensional structures in high-dimensional models where $p\\gg n$. Recently, there has been a surge of interest in connecting these threads in order to understand the behaviour of graphical models in high-dimensions. Due to their relative simplicity, undirected models such as ...
A Bayesian nonparametric approach to reconstruction and prediction of random dynamical systems
Merkatas, Christos; Kaloudis, Konstantinos; Hatjispyros, Spyridon J.
2017-06-01
We propose a Bayesian nonparametric mixture model for the reconstruction and prediction from observed time series data, of discretized stochastic dynamical systems, based on Markov Chain Monte Carlo methods. Our results can be used by researchers in physical modeling interested in a fast and accurate estimation of low dimensional stochastic models when the size of the observed time series is small and the noise process (perhaps) is non-Gaussian. The inference procedure is demonstrated specifically in the case of polynomial maps of an arbitrary degree and when a Geometric Stick Breaking mixture process prior over the space of densities, is applied to the additive errors. Our method is parsimonious compared to Bayesian nonparametric techniques based on Dirichlet process mixtures, flexible and general. Simulations based on synthetic time series are presented.
A Bayesian nonparametric approach to reconstruction and prediction of random dynamical systems.
Merkatas, Christos; Kaloudis, Konstantinos; Hatjispyros, Spyridon J
2017-06-01
We propose a Bayesian nonparametric mixture model for the reconstruction and prediction from observed time series data, of discretized stochastic dynamical systems, based on Markov Chain Monte Carlo methods. Our results can be used by researchers in physical modeling interested in a fast and accurate estimation of low dimensional stochastic models when the size of the observed time series is small and the noise process (perhaps) is non-Gaussian. The inference procedure is demonstrated specifically in the case of polynomial maps of an arbitrary degree and when a Geometric Stick Breaking mixture process prior over the space of densities, is applied to the additive errors. Our method is parsimonious compared to Bayesian nonparametric techniques based on Dirichlet process mixtures, flexible and general. Simulations based on synthetic time series are presented.
Bayesian methods for addressing long-standing problems in associative learning: The case of PREE.
Blanco, Fernando; Moris, Joaquín
2017-07-20
Most associative models typically assume that learning can be understood as a gradual change in associative strength that captures the situation into one single parameter, or representational state. We will call this view single-state learning. However, there is ample evidence showing that under many circumstances different relationships that share features can be learned independently, and animals can quickly switch between expressing one or another. We will call this multiple-state learning. Theoretically, it is understudied because it needs a different data analysis approach from those usually employed. In this paper, we present a Bayesian model of the Partial Reinforcement Extinction Effect (PREE) that can test the predictions of the multiple-state view. This implies estimating the moment of change in the responses (from the acquisition to the extinction performance), both at the individual and at the group levels. We used this model to analyze data from a PREE experiment with three levels of reinforcement during acquisition (100%, 75% and 50%). We found differences in the estimated moment of switch between states during extinction, so that it was delayed after leaner partial reinforcement schedules. The finding is compatible with the multiple-state view. It is the first time, to our knowledge, that the predictions from the multiple-state view are tested directly. The paper also aims to show the benefits that Bayesian methods can bring to the associative learning field.
Learning to Detect Traffic Incidents from Data Based on Tree Augmented Naive Bayesian Classifiers
Directory of Open Access Journals (Sweden)
Dawei Li
2017-01-01
Full Text Available This study develops a tree augmented naive Bayesian (TAN classifier based incident detection algorithm. Compared with the Bayesian networks based detection algorithms developed in the previous studies, this algorithm has less dependency on experts’ knowledge. The structure of TAN classifier for incident detection is learned from data. The discretization of continuous attributes is processed using an entropy-based method automatically. A simulation dataset on the section of the Ayer Rajah Expressway (AYE in Singapore is used to demonstrate the development of proposed algorithm, including wavelet denoising, normalization, entropy-based discretization, and structure learning. The performance of TAN based algorithm is evaluated compared with the previous developed Bayesian network (BN based and multilayer feed forward (MLF neural networks based algorithms with the same AYE data. The experiment results show that the TAN based algorithms perform better than the BN classifiers and have a similar performance to the MLF based algorithm. However, TAN based algorithm would have wider vista of applications because the theory of TAN classifiers is much less complicated than MLF. It should be found from the experiment that the TAN classifier based algorithm has a significant superiority over the speed of model training and calibration compared with MLF.
A Dynamic BI–Orthogonal Field Equation Approach to Efficient Bayesian Inversion
Directory of Open Access Journals (Sweden)
Tagade Piyush M.
2017-06-01
Full Text Available This paper proposes a novel computationally efficient stochastic spectral projection based approach to Bayesian inversion of a computer simulator with high dimensional parametric and model structure uncertainty. The proposed method is based on the decomposition of the solution into its mean and a random field using a generic Karhunen-Loève expansion. The random field is represented as a convolution of separable Hilbert spaces in stochastic and spatial dimensions that are spectrally represented using respective orthogonal bases. In particular, the present paper investigates generalized polynomial chaos bases for the stochastic dimension and eigenfunction bases for the spatial dimension. Dynamic orthogonality is used to derive closed-form equations for the time evolution of mean, spatial and the stochastic fields. The resultant system of equations consists of a partial differential equation (PDE that defines the dynamic evolution of the mean, a set of PDEs to define the time evolution of eigenfunction bases, while a set of ordinary differential equations (ODEs define dynamics of the stochastic field. This system of dynamic evolution equations efficiently propagates the prior parametric uncertainty to the system response. The resulting bi-orthogonal expansion of the system response is used to reformulate the Bayesian inference for efficient exploration of the posterior distribution. The efficacy of the proposed method is investigated for calibration of a 2D transient diffusion simulator with an uncertain source location and diffusivity. The computational efficiency of the method is demonstrated against a Monte Carlo method and a generalized polynomial chaos approach.
Yetton, Benjamin D; McDevitt, Elizabeth A; Cellini, Nicola; Shelton, Christian; Mednick, Sara C
2018-01-01
The pattern of sleep stages across a night (sleep architecture) is influenced by biological, behavioral, and clinical variables. However, traditional measures of sleep architecture such as stage proportions, fail to capture sleep dynamics. Here we quantify the impact of individual differences on the dynamics of sleep architecture and determine which factors or set of factors best predict the next sleep stage from current stage information. We investigated the influence of age, sex, body mass index, time of day, and sleep time on static (e.g. minutes in stage, sleep efficiency) and dynamic measures of sleep architecture (e.g. transition probabilities and stage duration distributions) using a large dataset of 3202 nights from a non-clinical population. Multi-level regressions show that sex effects duration of all Non-Rapid Eye Movement (NREM) stages, and age has a curvilinear relationship for Wake After Sleep Onset (WASO) and slow wave sleep (SWS) minutes. Bayesian network modeling reveals sleep architecture depends on time of day, total sleep time, age and sex, but not BMI. Older adults, and particularly males, have shorter bouts (more fragmentation) of Stage 2, SWS, and they transition less frequently to these stages. Additionally, we showed that the next sleep stage and its duration can be optimally predicted by the prior 2 stages and age. Our results demonstrate the potential benefit of big data and Bayesian network approaches in quantifying static and dynamic architecture of normal sleep.
Directory of Open Access Journals (Sweden)
Johannes Bill
Full Text Available During the last decade, Bayesian probability theory has emerged as a framework in cognitive science and neuroscience for describing perception, reasoning and learning of mammals. However, our understanding of how probabilistic computations could be organized in the brain, and how the observed connectivity structure of cortical microcircuits supports these calculations, is rudimentary at best. In this study, we investigate statistical inference and self-organized learning in a spatially extended spiking network model, that accommodates both local competitive and large-scale associative aspects of neural information processing, under a unified Bayesian account. Specifically, we show how the spiking dynamics of a recurrent network with lateral excitation and local inhibition in response to distributed spiking input, can be understood as sampling from a variational posterior distribution of a well-defined implicit probabilistic model. This interpretation further permits a rigorous analytical treatment of experience-dependent plasticity on the network level. Using machine learning theory, we derive update rules for neuron and synapse parameters which equate with Hebbian synaptic and homeostatic intrinsic plasticity rules in a neural implementation. In computer simulations, we demonstrate that the interplay of these plasticity rules leads to the emergence of probabilistic local experts that form distributed assemblies of similarly tuned cells communicating through lateral excitatory connections. The resulting sparse distributed spike code of a well-adapted network carries compressed information on salient input features combined with prior experience on correlations among them. Our theory predicts that the emergence of such efficient representations benefits from network architectures in which the range of local inhibition matches the spatial extent of pyramidal cells that share common afferent input.
Bill, Johannes; Buesing, Lars; Habenschuss, Stefan; Nessler, Bernhard; Maass, Wolfgang; Legenstein, Robert
2015-01-01
During the last decade, Bayesian probability theory has emerged as a framework in cognitive science and neuroscience for describing perception, reasoning and learning of mammals. However, our understanding of how probabilistic computations could be organized in the brain, and how the observed connectivity structure of cortical microcircuits supports these calculations, is rudimentary at best. In this study, we investigate statistical inference and self-organized learning in a spatially extended spiking network model, that accommodates both local competitive and large-scale associative aspects of neural information processing, under a unified Bayesian account. Specifically, we show how the spiking dynamics of a recurrent network with lateral excitation and local inhibition in response to distributed spiking input, can be understood as sampling from a variational posterior distribution of a well-defined implicit probabilistic model. This interpretation further permits a rigorous analytical treatment of experience-dependent plasticity on the network level. Using machine learning theory, we derive update rules for neuron and synapse parameters which equate with Hebbian synaptic and homeostatic intrinsic plasticity rules in a neural implementation. In computer simulations, we demonstrate that the interplay of these plasticity rules leads to the emergence of probabilistic local experts that form distributed assemblies of similarly tuned cells communicating through lateral excitatory connections. The resulting sparse distributed spike code of a well-adapted network carries compressed information on salient input features combined with prior experience on correlations among them. Our theory predicts that the emergence of such efficient representations benefits from network architectures in which the range of local inhibition matches the spatial extent of pyramidal cells that share common afferent input. PMID:26284370
Directory of Open Access Journals (Sweden)
Heidi L. Tessmer
2018-03-01
Full Text Available To estimate and predict the transmission dynamics of respiratory viruses, the estimation of the basic reproduction number, R0, is essential. Recently, approximate Bayesian computation methods have been used as likelihood free methods to estimate epidemiological model parameters, particularly R0. In this paper, we explore various machine learning approaches, the multi-layer perceptron, convolutional neural network, and long-short term memory, to learn and estimate the parameters. Further, we compare the accuracy of the estimates and time requirements for machine learning and the approximate Bayesian computation methods on both simulated and real-world epidemiological data from outbreaks of influenza A(H1N1pdm09, mumps, and measles. We find that the machine learning approaches can be verified and tested faster than the approximate Bayesian computation method, but that the approximate Bayesian computation method is more robust across different datasets.
A Bayesian Developmental Approach to Robotic Goal-Based Imitation Learning.
Directory of Open Access Journals (Sweden)
Michael Jae-Yoon Chung
Full Text Available A fundamental challenge in robotics today is building robots that can learn new skills by observing humans and imitating human actions. We propose a new Bayesian approach to robotic learning by imitation inspired by the developmental hypothesis that children use self-experience to bootstrap the process of intention recognition and goal-based imitation. Our approach allows an autonomous agent to: (i learn probabilistic models of actions through self-discovery and experience, (ii utilize these learned models for inferring the goals of human actions, and (iii perform goal-based imitation for robotic learning and human-robot collaboration. Such an approach allows a robot to leverage its increasing repertoire of learned behaviors to interpret increasingly complex human actions and use the inferred goals for imitation, even when the robot has very different actuators from humans. We demonstrate our approach using two different scenarios: (i a simulated robot that learns human-like gaze following behavior, and (ii a robot that learns to imitate human actions in a tabletop organization task. In both cases, the agent learns a probabilistic model of its own actions, and uses this model for goal inference and goal-based imitation. We also show that the robotic agent can use its probabilistic model to seek human assistance when it recognizes that its inferred actions are too uncertain, risky, or impossible to perform, thereby opening the door to human-robot collaboration.
A dynamic Bayesian network based approach to safety decision support in tunnel construction
International Nuclear Information System (INIS)
Wu, Xianguo; Liu, Huitao; Zhang, Limao; Skibniewski, Miroslaw J.; Deng, Qianli; Teng, Jiaying
2015-01-01
This paper presents a systemic decision approach with step-by-step procedures based on dynamic Bayesian network (DBN), aiming to provide guidelines for dynamic safety analysis of the tunnel-induced road surface damage over time. The proposed DBN-based approach can accurately illustrate the dynamic and updated feature of geological, design and mechanical variables as the construction progress evolves, in order to overcome deficiencies of traditional fault analysis methods. Adopting the predictive, sensitivity and diagnostic analysis techniques in the DBN inference, this approach is able to perform feed-forward, concurrent and back-forward control respectively on a quantitative basis, and provide real-time support before and after an accident. A case study in relating to dynamic safety analysis in the construction of Wuhan Yangtze Metro Tunnel in China is used to verify the feasibility of the proposed approach, as well as its application potential. The relationships between the DBN-based and BN-based approaches are further discussed according to analysis results. The proposed approach can be used as a decision tool to provide support for safety analysis in tunnel construction, and thus increase the likelihood of a successful project in a dynamic project environment. - Highlights: • A dynamic Bayesian network (DBN) based approach for safety decision support is developed. • This approach is able to perform feed-forward, concurrent and back-forward analysis and control. • A case concerning dynamic safety analysis in Wuhan Yangtze Metro Tunnel in China is presented. • DBN-based approach can perform a higher accuracy than traditional static BN-based approach
Improved resolution and reliability in dynamic PET using Bayesian regularization of MRTM2
DEFF Research Database (Denmark)
Agn, Mikael; Svarer, Claus; Frokjaer, Vibe G.
2014-01-01
This paper presents a mathematical model that regularizes dynamic PET data by using a Bayesian framework. We base the model on the well known two-parameter multilinear reference tissue method MRTM2 and regularize on the assumption that spatially close regions have similar parameters. The developed...... model is compared to the conventional approach of improving the low signal-to-noise ratio of PET data, i.e., spatial filtering of each time frame independently by a Gaussian kernel. We show that the model handles high levels of noise better than the conventional approach, while at the same time...
A Bayesian Model of Biases in Artificial Language Learning: The Case of a Word-Order Universal
Culbertson, Jennifer; Smolensky, Paul
2012-01-01
In this article, we develop a hierarchical Bayesian model of learning in a general type of artificial language-learning experiment in which learners are exposed to a mixture of grammars representing the variation present in real learners' input, particularly at times of language change. The modeling goal is to formalize and quantify hypothesized…
McGeachie, Michael J; Chang, Hsun-Hsien; Weiss, Scott T
2014-06-01
Bayesian Networks (BN) have been a popular predictive modeling formalism in bioinformatics, but their application in modern genomics has been slowed by an inability to cleanly handle domains with mixed discrete and continuous variables. Existing free BN software packages either discretize continuous variables, which can lead to information loss, or do not include inference routines, which makes prediction with the BN impossible. We present CGBayesNets, a BN package focused around prediction of a clinical phenotype from mixed discrete and continuous variables, which fills these gaps. CGBayesNets implements Bayesian likelihood and inference algorithms for the conditional Gaussian Bayesian network (CGBNs) formalism, one appropriate for predicting an outcome of interest from, e.g., multimodal genomic data. We provide four different network learning algorithms, each making a different tradeoff between computational cost and network likelihood. CGBayesNets provides a full suite of functions for model exploration and verification, including cross validation, bootstrapping, and AUC manipulation. We highlight several results obtained previously with CGBayesNets, including predictive models of wood properties from tree genomics, leukemia subtype classification from mixed genomic data, and robust prediction of intensive care unit mortality outcomes from metabolomic profiles. We also provide detailed example analysis on public metabolomic and gene expression datasets. CGBayesNets is implemented in MATLAB and available as MATLAB source code, under an Open Source license and anonymous download at http://www.cgbayesnets.com.
The social Bayesian brain: does mentalizing make a difference when we learn?
Directory of Open Access Journals (Sweden)
Marie Devaine
2014-12-01
Full Text Available When it comes to interpreting others' behaviour, we almost irrepressibly engage in the attribution of mental states (beliefs, emotions…. Such "mentalizing" can become very sophisticated, eventually endowing us with highly adaptive skills such as convincing, teaching or deceiving. Here, sophistication can be captured in terms of the depth of our recursive beliefs, as in "I think that you think that I think…" In this work, we test whether such sophisticated recursive beliefs subtend learning in the context of social interaction. We asked participants to play repeated games against artificial (Bayesian mentalizing agents, which differ in their sophistication. Critically, we made people believe either that they were playing against each other, or that they were gambling like in a casino. Although both framings are similarly deceiving, participants win against the artificial (sophisticated mentalizing agents in the social framing of the task, and lose in the non-social framing. Moreover, we find that participants' choice sequences are best explained by sophisticated mentalizing Bayesian learning models only in the social framing. This study is the first demonstration of the added-value of mentalizing on learning in the context of repeated social interactions. Importantly, our results show that we would not be able to decipher intentional behaviour without a priori attributing mental states to others.
Observing the observer (I): meta-bayesian models of learning and decision-making.
Daunizeau, Jean; den Ouden, Hanneke E M; Pessiglione, Matthias; Kiebel, Stefan J; Stephan, Klaas E; Friston, Karl J
2010-12-14
In this paper, we present a generic approach that can be used to infer how subjects make optimal decisions under uncertainty. This approach induces a distinction between a subject's perceptual model, which underlies the representation of a hidden "state of affairs" and a response model, which predicts the ensuing behavioural (or neurophysiological) responses to those inputs. We start with the premise that subjects continuously update a probabilistic representation of the causes of their sensory inputs to optimise their behaviour. In addition, subjects have preferences or goals that guide decisions about actions given the above uncertain representation of these hidden causes or state of affairs. From a Bayesian decision theoretic perspective, uncertain representations are so-called "posterior" beliefs, which are influenced by subjective "prior" beliefs. Preferences and goals are encoded through a "loss" (or "utility") function, which measures the cost incurred by making any admissible decision for any given (hidden) state of affair. By assuming that subjects make optimal decisions on the basis of updated (posterior) beliefs and utility (loss) functions, one can evaluate the likelihood of observed behaviour. Critically, this enables one to "observe the observer", i.e. identify (context- or subject-dependent) prior beliefs and utility-functions using psychophysical or neurophysiological measures. In this paper, we describe the main theoretical components of this meta-Bayesian approach (i.e. a Bayesian treatment of Bayesian decision theoretic predictions). In a companion paper ('Observing the observer (II): deciding when to decide'), we describe a concrete implementation of it and demonstrate its utility by applying it to simulated and real reaction time data from an associative learning task.
Observing the observer (I: meta-bayesian models of learning and decision-making.
Directory of Open Access Journals (Sweden)
Jean Daunizeau
2010-12-01
Full Text Available In this paper, we present a generic approach that can be used to infer how subjects make optimal decisions under uncertainty. This approach induces a distinction between a subject's perceptual model, which underlies the representation of a hidden "state of affairs" and a response model, which predicts the ensuing behavioural (or neurophysiological responses to those inputs. We start with the premise that subjects continuously update a probabilistic representation of the causes of their sensory inputs to optimise their behaviour. In addition, subjects have preferences or goals that guide decisions about actions given the above uncertain representation of these hidden causes or state of affairs. From a Bayesian decision theoretic perspective, uncertain representations are so-called "posterior" beliefs, which are influenced by subjective "prior" beliefs. Preferences and goals are encoded through a "loss" (or "utility" function, which measures the cost incurred by making any admissible decision for any given (hidden state of affair. By assuming that subjects make optimal decisions on the basis of updated (posterior beliefs and utility (loss functions, one can evaluate the likelihood of observed behaviour. Critically, this enables one to "observe the observer", i.e. identify (context- or subject-dependent prior beliefs and utility-functions using psychophysical or neurophysiological measures. In this paper, we describe the main theoretical components of this meta-Bayesian approach (i.e. a Bayesian treatment of Bayesian decision theoretic predictions. In a companion paper ('Observing the observer (II: deciding when to decide', we describe a concrete implementation of it and demonstrate its utility by applying it to simulated and real reaction time data from an associative learning task.
Reliability modelling and analysis of a multi-state element based on a dynamic Bayesian network
Li, Zhiqiang; Xu, Tingxue; Gu, Junyuan; Dong, Qi; Fu, Linyu
2018-04-01
This paper presents a quantitative reliability modelling and analysis method for multi-state elements based on a combination of the Markov process and a dynamic Bayesian network (DBN), taking perfect repair, imperfect repair and condition-based maintenance (CBM) into consideration. The Markov models of elements without repair and under CBM are established, and an absorbing set is introduced to determine the reliability of the repairable element. According to the state-transition relations between the states determined by the Markov process, a DBN model is built. In addition, its parameters for series and parallel systems, namely, conditional probability tables, can be calculated by referring to the conditional degradation probabilities. Finally, the power of a control unit in a failure model is used as an example. A dynamic fault tree (DFT) is translated into a Bayesian network model, and subsequently extended to a DBN. The results show the state probabilities of an element and the system without repair, with perfect and imperfect repair, and under CBM, with an absorbing set plotted by differential equations and verified. Through referring forward, the reliability value of the control unit is determined in different kinds of modes. Finally, weak nodes are noted in the control unit.
Dynamic probability evaluation of safety levels of earth-rockfill dams using Bayesian approach
Directory of Open Access Journals (Sweden)
Zi-wu Fan
2009-06-01
Full Text Available In order to accurately predict and control the aging process of dams, new information should be collected continuously to renew the quantitative evaluation of dam safety levels. Owing to the complex structural characteristics of dams, it is quite difficult to predict the time-varying factors affecting their safety levels. It is not feasible to employ dynamic reliability indices to evaluate the actual safety levels of dams. Based on the relevant regulations for dam safety classification in China, a dynamic probability description of dam safety levels was developed. Using the Bayesian approach and effective information mining, as well as real-time information, this study achieved more rational evaluation and prediction of dam safety levels. With the Bayesian expression of discrete stochastic variables, the a priori probabilities of the dam safety levels determined by experts were combined with the likelihood probability of the real-time check information, and the probability information for the evaluation of dam safety levels was renewed. The probability index was then applied to dam rehabilitation decision-making. This method helps reduce the difficulty and uncertainty of the evaluation of dam safety levels and complies with the current safe decision-making regulations for dams in China. It also enhances the application of current risk analysis methods for dam safety levels.
Zeng, Xueqiang; Luo, Gang
2017-12-01
Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge and many labor-intensive manual iterations. To lower the bar to machine learning, miscellaneous automatic selection methods for algorithms and/or hyper-parameter values have been proposed. Existing automatic selection methods are inefficient on large data sets. This poses a challenge for using machine learning in the clinical big data era. To address the challenge, this paper presents progressive sampling-based Bayesian optimization, an efficient and automatic selection method for both algorithms and hyper-parameter values. We report an implementation of the method. We show that compared to a state of the art automatic selection method, our method can significantly reduce search time, classification error rate, and standard deviation of error rate due to randomization. This is major progress towards enabling fast turnaround in identifying high-quality solutions required by many machine learning-based clinical data analysis tasks.
Directory of Open Access Journals (Sweden)
Huu eHoang
2015-05-01
Full Text Available The inverse problem for estimating model parameters from brain spike data is an ill-posed problem because of a huge mismatch in the system complexity between the model and the brain as well as its non-stationary dynamics, and needs a stochastic approach that finds the most likely solution among many possible solutions. In the present study, we developed a segmental Bayesian method to estimate the two parameters of interest, the gap-junctional (gc and inhibitory conductance (gi from inferior olive spike data. Feature vectors were estimated for the spike data in a segment-wise fashion to compensate for the non-stationary firing dynamics. Hierarchical Bayesian estimation was conducted to estimate the gc and gi for every spike segment using a forward model constructed in the principal component analysis (PCA space of the feature vectors, and to merge the segmental estimates into single estimates for every neuron. The segmental Bayesian estimation gave smaller fitting errors than the conventional Bayesian inference, which finds the estimates once across the entire spike data, or the minimum error method, which directly finds the closest match in the PCA space. The segmental Bayesian inference has the potential to overcome the problem of non-stationary dynamics and resolve the ill-posedness of the inverse problem because of the mismatch between the model and the brain under the constraints based, and it is a useful tool to evaluate parameters of interest for neuroscience from experimental spike train data.
Bayesian artificial intelligence
Korb, Kevin B
2003-01-01
As the power of Bayesian techniques has become more fully realized, the field of artificial intelligence has embraced Bayesian methodology and integrated it to the point where an introduction to Bayesian techniques is now a core course in many computer science programs. Unlike other books on the subject, Bayesian Artificial Intelligence keeps mathematical detail to a minimum and covers a broad range of topics. The authors integrate all of Bayesian net technology and learning Bayesian net technology and apply them both to knowledge engineering. They emphasize understanding and intuition but also provide the algorithms and technical background needed for applications. Software, exercises, and solutions are available on the authors' website.
Constrained Bayesian Active Learning of Interference Channels in Cognitive Radio Networks
Tsakmalis, Anestis; Chatzinotas, Symeon; Ottersten, Bjorn
2018-02-01
In this paper, a sequential probing method for interference constraint learning is proposed to allow a centralized Cognitive Radio Network (CRN) accessing the frequency band of a Primary User (PU) in an underlay cognitive scenario with a designed PU protection specification. The main idea is that the CRN probes the PU and subsequently eavesdrops the reverse PU link to acquire the binary ACK/NACK packet. This feedback indicates whether the probing-induced interference is harmful or not and can be used to learn the PU interference constraint. The cognitive part of this sequential probing process is the selection of the power levels of the Secondary Users (SUs) which aims to learn the PU interference constraint with a minimum number of probing attempts while setting a limit on the number of harmful probing-induced interference events or equivalently of NACK packet observations over a time window. This constrained design problem is studied within the Active Learning (AL) framework and an optimal solution is derived and implemented with a sophisticated, accurate and fast Bayesian Learning method, the Expectation Propagation (EP). The performance of this solution is also demonstrated through numerical simulations and compared with modified versions of AL techniques we developed in earlier work.
Furfaro, R.; Linares, R.; Gaylor, D.; Jah, M.; Walls, R.
2016-09-01
In this paper, we present an end-to-end approach that employs machine learning techniques and Ontology-based Bayesian Networks (BN) to characterize the behavior of resident space objects. State-of-the-Art machine learning architectures (e.g. Extreme Learning Machines, Convolutional Deep Networks) are trained on physical models to learn the Resident Space Object (RSO) features in the vectorized energy and momentum states and parameters. The mapping from measurements to vectorized energy and momentum states and parameters enables behavior characterization via clustering in the features space and subsequent RSO classification. Additionally, Space Object Behavioral Ontologies (SOBO) are employed to define and capture the domain knowledge-base (KB) and BNs are constructed from the SOBO in a semi-automatic fashion to execute probabilistic reasoning over conclusions drawn from trained classifiers and/or directly from processed data. Such an approach enables integrating machine learning classifiers and probabilistic reasoning to support higher-level decision making for space domain awareness applications. The innovation here is to use these methods (which have enjoyed great success in other domains) in synergy so that it enables a "from data to discovery" paradigm by facilitating the linkage and fusion of large and disparate sources of information via a Big Data Science and Analytics framework.
Reconstructing constructivism: causal models, Bayesian learning mechanisms, and the theory theory.
Gopnik, Alison; Wellman, Henry M
2012-11-01
We propose a new version of the "theory theory" grounded in the computational framework of probabilistic causal models and Bayesian learning. Probabilistic models allow a constructivist but rigorous and detailed approach to cognitive development. They also explain the learning of both more specific causal hypotheses and more abstract framework theories. We outline the new theoretical ideas, explain the computational framework in an intuitive and nontechnical way, and review an extensive but relatively recent body of empirical results that supports these ideas. These include new studies of the mechanisms of learning. Children infer causal structure from statistical information, through their own actions on the world and through observations of the actions of others. Studies demonstrate these learning mechanisms in children from 16 months to 4 years old and include research on causal statistical learning, informal experimentation through play, and imitation and informal pedagogy. They also include studies of the variability and progressive character of intuitive theory change, particularly theory of mind. These studies investigate both the physical and the psychological and social domains. We conclude with suggestions for further collaborative projects between developmental and computational cognitive scientists.
Accuracy of latent-variable estimation in Bayesian semi-supervised learning.
Yamazaki, Keisuke
2015-09-01
Hierarchical probabilistic models, such as Gaussian mixture models, are widely used for unsupervised learning tasks. These models consist of observable and latent variables, which represent the observable data and the underlying data-generation process, respectively. Unsupervised learning tasks, such as cluster analysis, are regarded as estimations of latent variables based on the observable ones. The estimation of latent variables in semi-supervised learning, where some labels are observed, will be more precise than that in unsupervised, and one of the concerns is to clarify the effect of the labeled data. However, there has not been sufficient theoretical analysis of the accuracy of the estimation of latent variables. In a previous study, a distribution-based error function was formulated, and its asymptotic form was calculated for unsupervised learning with generative models. It has been shown that, for the estimation of latent variables, the Bayes method is more accurate than the maximum-likelihood method. The present paper reveals the asymptotic forms of the error function in Bayesian semi-supervised learning for both discriminative and generative models. The results show that the generative model, which uses all of the given data, performs better when the model is well specified. Copyright © 2015 Elsevier Ltd. All rights reserved.
Ranking Features on Psychological Dynamics of Cooperative Team Work through Bayesian Networks
Directory of Open Access Journals (Sweden)
Pilar Fuster-Parra
2016-05-01
Full Text Available The aim of this study is to rank some features that characterize the psychological dynamics of cooperative team work in order to determine priorities for interventions and formation: leading positive feedback, cooperative manager and collaborative manager features. From a dataset of 20 cooperative sport teams (403 soccer players, the characteristics of the prototypical sports teams are studied using an average Bayesian network (BN and two special types of BNs, the Bayesian classifiers: naive Bayes (NB and tree augmented naive Bayes (TAN. BNs are selected as they are able to produce probability estimates rather than predictions. BN results show that the antecessors (the “top” features ranked are the team members’ expectations and their attraction to the social aspects of the task. The main node is formed by the cooperative behaviors, the consequences ranked at the BN bottom (ratified by the TAN trees and the instantiations made, the roles assigned to the members and their survival inside the same team. These results should help managers to determine contents and priorities when they have to face team-building actions.
Introduction to Bayesian statistics
Bolstad, William M
2017-01-01
There is a strong upsurge in the use of Bayesian methods in applied statistical analysis, yet most introductory statistics texts only present frequentist methods. Bayesian statistics has many important advantages that students should learn about if they are going into fields where statistics will be used. In this Third Edition, four newly-added chapters address topics that reflect the rapid advances in the field of Bayesian staistics. The author continues to provide a Bayesian treatment of introductory statistical topics, such as scientific data gathering, discrete random variables, robust Bayesian methods, and Bayesian approaches to inferenfe cfor discrete random variables, bionomial proprotion, Poisson, normal mean, and simple linear regression. In addition, newly-developing topics in the field are presented in four new chapters: Bayesian inference with unknown mean and variance; Bayesian inference for Multivariate Normal mean vector; Bayesian inference for Multiple Linear RegressionModel; and Computati...
Muscle cocontraction following dynamics learning.
Darainy, Mohammad; Ostry, David J
2008-09-01
Coactivation of antagonist muscles is readily observed early in motor learning, in interactions with unstable mechanical environments and in motor system pathologies. Here we present evidence that the nervous system uses coactivation control far more extensively and that patterns of cocontraction during movement are closely tied to the specific requirements of the task. We have examined the changes in cocontraction that follow dynamics learning in tasks that are thought to involve finely sculpted feedforward adjustments to motor commands. We find that, even following substantial training, cocontraction varies in a systematic way that depends on both movement direction and the strength of the external load. The proportion of total activity that is due to cocontraction nevertheless remains remarkably constant. Moreover, long after indices of motor learning and electromyographic measures have reached asymptotic levels, cocontraction still accounts for a significant proportion of total muscle activity in all phases of movement and in all load conditions. These results show that even following dynamics learning in predictable and stable environments, cocontraction forms a central part of the means by which the nervous system regulates movement.
Dynamics of the evolution of learning algorithms by selection
International Nuclear Information System (INIS)
Neirotti, Juan Pablo; Caticha, Nestor
2003-01-01
We study the evolution of artificial learning systems by means of selection. Genetic programming is used to generate populations of programs that implement algorithms used by neural network classifiers to learn a rule in a supervised learning scenario. In contrast to concentrating on final results, which would be the natural aim while designing good learning algorithms, we study the evolution process. Phenotypic and genotypic entropies, which describe the distribution of fitness and of symbols, respectively, are used to monitor the dynamics. We identify significant functional structures responsible for the improvements in the learning process. In particular, some combinations of variables and operators are useful in assessing performance in rule extraction and can thus implement annealing of the learning schedule. We also find combinations that can signal surprise, measured on a single example, by the difference between predicted and correct classification. When such favorable structures appear, they are disseminated on very short time scales throughout the population. Due to such abruptness they can be thought of as dynamical transitions. But foremost, we find a strict temporal order of such discoveries. Structures that measure performance are never useful before those for measuring surprise. Invasions of the population by such structures in the reverse order were never observed. Asymptotically, the generalization ability approaches Bayesian results
Multi-population genomic prediction using a multi-task Bayesian learning model.
Chen, Liuhong; Li, Changxi; Miller, Stephen; Schenkel, Flavio
2014-05-03
Genomic prediction in multiple populations can be viewed as a multi-task learning problem where tasks are to derive prediction equations for each population and multi-task learning property can be improved by sharing information across populations. The goal of this study was to develop a multi-task Bayesian learning model for multi-population genomic prediction with a strategy to effectively share information across populations. Simulation studies and real data from Holstein and Ayrshire dairy breeds with phenotypes on five milk production traits were used to evaluate the proposed multi-task Bayesian learning model and compare with a single-task model and a simple data pooling method. A multi-task Bayesian learning model was proposed for multi-population genomic prediction. Information was shared across populations through a common set of latent indicator variables while SNP effects were allowed to vary in different populations. Both simulation studies and real data analysis showed the effectiveness of the multi-task model in improving genomic prediction accuracy for the smaller Ayshire breed. Simulation studies suggested that the multi-task model was most effective when the number of QTL was small (n = 20), with an increase of accuracy by up to 0.09 when QTL effects were lowly correlated between two populations (ρ = 0.2), and up to 0.16 when QTL effects were highly correlated (ρ = 0.8). When QTL genotypes were included for training and validation, the improvements were 0.16 and 0.22, respectively, for scenarios of the low and high correlation of QTL effects between two populations. When the number of QTL was large (n = 200), improvement was small with a maximum of 0.02 when QTL genotypes were not included for genomic prediction. Reduction in accuracy was observed for the simple pooling method when the number of QTL was small and correlation of QTL effects between the two populations was low. For the real data, the multi-task model achieved an
A Dynamic Logic for Learning Theory
DEFF Research Database (Denmark)
Baltag, Alexandru; Gierasimczuk, Nina; Özgün, Aybüke
2017-01-01
Building on previous work that bridged Formal Learning Theory and Dynamic Epistemic Logic in a topological setting, we introduce a Dynamic Logic for Learning Theory (DLLT), extending Subset Space Logics with dynamic observation modalities, as well as with a learning operator, which encodes the le...... the learner’s conjecture after observing a finite sequence of data. We completely axiomatise DLLT, study its expressivity and use it to characterise various notions of knowledge, belief, and learning. ...
Grzegorczyk, Marco; Husmeier, Dirk
2012-01-01
An important and challenging problem in systems biology is the inference of gene regulatory networks from short non-stationary time series of transcriptional profiles. A popular approach that has been widely applied to this end is based on dynamic Bayesian networks (DBNs), although traditional
A novel critical infrastructure resilience assessment approach using dynamic Bayesian networks
Cai, Baoping; Xie, Min; Liu, Yonghong; Liu, Yiliu; Ji, Renjie; Feng, Qiang
2017-10-01
The word resilience originally originates from the Latin word "resiliere", which means to "bounce back". The concept has been used in various fields, such as ecology, economics, psychology, and society, with different definitions. In the field of critical infrastructure, although some resilience metrics are proposed, they are totally different from each other, which are determined by the performances of the objects of evaluation. Here we bridge the gap by developing a universal critical infrastructure resilience metric from the perspective of reliability engineering. A dynamic Bayesian networks-based assessment approach is proposed to calculate the resilience value. A series, parallel and voting system is used to demonstrate the application of the developed resilience metric and assessment approach.
Directory of Open Access Journals (Sweden)
D.O. Olayungbo
2016-12-01
Full Text Available This paper examines the dynamic interactions between insurance and economic growth in eight African countries for the period of 1970–2013. Insurance demand is measured by insurance penetration which accounts for income differences across the sample countries. A Bayesian Time Varying Parameter Vector Auto regression (TVP-VAR model with stochastic volatility is used to analyze the short run and the long run among the variables of interest. Using insurance penetration as a measure of insurance to economic growth, we find positive relationship for Egypt, while short-run negative and long-run positive effects are found for Kenya, Mauritius, and South Africa. On the contrary, negative effects are found for Algeria, Nigeria, Tunisia, and Zimbabwe. Implementation of sound financial reforms and wide insurance coverage are proposed recommendations for insurance development in the selected African countries.
Soufan, Othman; Ba Alawi, Wail; Afeef, Moataz A.; Essack, Magbubah; Kalnis, Panos; Bajic, Vladimir B.
2016-01-01
of compounds that were not tested in particular assays. Results Here we present DRABAL, a novel MLC solution that incorporates structure learning of a Bayesian network as a step to model dependency between the HTS assays. In this study, DRABAL was used
Use of dynamic Bayesian networks for life extension assessment of ageing systems
International Nuclear Information System (INIS)
Ramírez, Pedro A. Pérez; Utne, Ingrid Bouwer
2015-01-01
Extending the operating lifetime of ageing technical systems is of great interest for industrial applications. Life extension requires identifying and selecting decision alternatives which allow for a safe and economic operation of the system beyond its design lifetime. This article proposes a dynamic Bayesian network for assessing the life extension of ageing repairable systems. The main objective of the model is to provide decision support based on the system performance during a finite time horizon, which is defined by the life extension period. The model has three main applications: (i) assessing and selecting optimal decision alternatives for the life extension at present time, based on historical data; (ii) identifying and minimizing the factors that have a negative impact on the system performance; and (iii) reassessing and optimizing the decision alternatives during operation throughout the life extension period, based on updating the model with new operational data gathered. A case study illustrates the application of the model for life extension of a real firewater pump system in an oil and gas facility. The case study analyzes three decision alternatives, where preventive maintenance and functional test policies are optimized, and the uncertainty involved in each alternative is computed. - Highlights: • A dynamic Bayesian network is used for predicting the system performance. • The performance is measured with relevant variables: cost; unavailability; safety. • The model can be used when scarce data is available, no degradation data is needed. • The uncertainty associated to each alternative is computed in the model. • A detailed case study of a real safety system shows the applicability of the model
International Nuclear Information System (INIS)
Khakzad, Nima
2015-01-01
A domino effect is a low frequency high consequence chain of accidents where a primary accident (usually fire and explosion) in a unit triggers secondary accidents in adjacent units. High complexity and growing interdependencies of chemical infrastructures make them increasingly vulnerable to domino effects. Domino effects can be considered as time dependent processes. Thus, not only the identification of involved units but also their temporal entailment in the chain of accidents matter. More importantly, in the case of domino-induced fires which can generally last much longer compared to explosions, foreseeing the temporal evolution of domino effects and, in particular, predicting the most probable sequence of accidents (or involved units) in a domino effect can be of significance in the allocation of preventive and protective safety measures. Although many attempts have been made to identify the spatial evolution of domino effects, the temporal evolution of such accidents has been overlooked. We have proposed a methodology based on dynamic Bayesian network to model both the spatial and temporal evolutions of domino effects and also to quantify the most probable sequence of accidents in a potential domino effect. The application of the developed methodology has been demonstrated via a hypothetical fuel storage plant. - Highlights: • A Dynamic Bayesian Network methodology has been developed to model domino effects. • Considering time-dependencies, both spatial and temporal evolutions of domino effects have been modeled. • The concept of most probable sequence of accidents has been proposed instead of the most probable combination of accidents. • Using backward analysis, the most vulnerable units have been identified during a potential domino effect. • The proposed methodology does not need to identify a unique primary unit (accident) for domino effect modeling
Direction-of-Arrival Estimation for Coherent Sources via Sparse Bayesian Learning
Directory of Open Access Journals (Sweden)
Zhang-Meng Liu
2014-01-01
Full Text Available A spatial filtering-based relevance vector machine (RVM is proposed in this paper to separate coherent sources and estimate their directions-of-arrival (DOA, with the filter parameters and DOA estimates initialized and refined via sparse Bayesian learning. The RVM is used to exploit the spatial sparsity of the incident signals and gain improved adaptability to much demanding scenarios, such as low signal-to-noise ratio (SNR, limited snapshots, and spatially adjacent sources, and the spatial filters are introduced to enhance global convergence of the original RVM in the case of coherent sources. The proposed method adapts to arbitrary array geometry, and simulation results show that it surpasses the existing methods in DOA estimation performance.
Bayesian methods for the physical sciences learning from examples in astronomy and physics
Andreon, Stefano
2015-01-01
Statistical literacy is critical for the modern researcher in Physics and Astronomy. This book empowers researchers in these disciplines by providing the tools they will need to analyze their own data. Chapters in this book provide a statistical base from which to approach new problems, including numerical advice and a profusion of examples. The examples are engaging analyses of real-world problems taken from modern astronomical research. The examples are intended to be starting points for readers as they learn to approach their own data and research questions. Acknowledging that scientific progress now hinges on the availability of data and the possibility to improve previous analyses, data and code are distributed throughout the book. The JAGS symbolic language used throughout the book makes it easy to perform Bayesian analysis and is particularly valuable as readers may use it in a myriad of scenarios through slight modifications.
On open questions in the geometric approach to structural learning Bayesian nets
Czech Academy of Sciences Publication Activity Database
Studený, Milan; Vomlel, Jiří
2011-01-01
Roč. 52, č. 5 (2011), s. 627-640 ISSN 0888-613X. [Workshop on Uncertainty Processing WUPES'09 /8./. Liblice, 19.09.2009-23.09.2009] R&D Projects: GA MŠk(CZ) 1M0572; GA ČR GA201/08/0539; GA ČR GEICC/08/E010 Grant - others:GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : structural learning Bayesian nets * standard imset * polytope * geometric neighborhood * differential imset Subject RIV: BA - General Mathematics Impact factor: 1.948, year: 2011 http://library.utia.cas.cz/separaty/2011/MTR/studeny-0358907. pdf
Learning Bayesian network classifiers for credit scoring using Markov Chain Monte Carlo search
Baesens, B.; Egmont-Petersen, M.; Castelo, R.; Vanthienen, J.
2001-01-01
In this paper, we will evaluate the power and usefulness of Bayesian network classifiers for credit scoring. Various types of Bayesian network classifiers will be evaluated and contrasted including unrestricted Bayesian network classifiers learnt using Markov Chain Monte Carlo (MCMC) search.
Bayesian dynamic modeling of time series of dengue disease case counts.
Martínez-Bello, Daniel Adyro; López-Quílez, Antonio; Torres-Prieto, Alexander
2017-07-01
The aim of this study is to model the association between weekly time series of dengue case counts and meteorological variables, in a high-incidence city of Colombia, applying Bayesian hierarchical dynamic generalized linear models over the period January 2008 to August 2015. Additionally, we evaluate the model's short-term performance for predicting dengue cases. The methodology shows dynamic Poisson log link models including constant or time-varying coefficients for the meteorological variables. Calendar effects were modeled using constant or first- or second-order random walk time-varying coefficients. The meteorological variables were modeled using constant coefficients and first-order random walk time-varying coefficients. We applied Markov Chain Monte Carlo simulations for parameter estimation, and deviance information criterion statistic (DIC) for model selection. We assessed the short-term predictive performance of the selected final model, at several time points within the study period using the mean absolute percentage error. The results showed the best model including first-order random walk time-varying coefficients for calendar trend and first-order random walk time-varying coefficients for the meteorological variables. Besides the computational challenges, interpreting the results implies a complete analysis of the time series of dengue with respect to the parameter estimates of the meteorological effects. We found small values of the mean absolute percentage errors at one or two weeks out-of-sample predictions for most prediction points, associated with low volatility periods in the dengue counts. We discuss the advantages and limitations of the dynamic Poisson models for studying the association between time series of dengue disease and meteorological variables. The key conclusion of the study is that dynamic Poisson models account for the dynamic nature of the variables involved in the modeling of time series of dengue disease, producing useful
Bayesian Evaluation of Dynamical Soil Carbon Models Using Soil Carbon Flux Data
Xie, H. W.; Romero-Olivares, A.; Guindani, M.; Allison, S. D.
2017-12-01
2016 was Earth's hottest year in the modern temperature record and the third consecutive record-breaking year. As the planet continues to warm, temperature-induced changes in respiration rates of soil microbes could reduce the amount of carbon sequestered in the soil organic carbon (SOC) pool, one of the largest terrestrial stores of carbon. This would accelerate temperature increases. In order to predict the future size of the SOC pool, mathematical soil carbon models (SCMs) describing interactions between the biosphere and atmosphere are needed. SCMs must be validated before they can be chosen for predictive use. In this study, we check two SCMs called CON and AWB for consistency with observed data using Bayesian goodness of fit testing that can be used in the future to compare other models. We compare the fit of the models to longitudinal soil respiration data from a meta-analysis of soil heating experiments using a family of Bayesian goodness of fit metrics called information criteria (IC), including the Widely Applicable Information Criterion (WAIC), the Leave-One-Out Information Criterion (LOOIC), and the Log Pseudo Marginal Likelihood (LPML). These IC's take the entire posterior distribution into account, rather than just one outputted model fit line. A lower WAIC and LOOIC and larger LPML indicate a better fit. We compare AWB and CON with fixed steady state model pool sizes. At equivalent SOC, dissolved organic carbon, and microbial pool sizes, CON always outperforms AWB quantitatively by all three IC's used. AWB monotonically improves in fit as we reduce the SOC steady state pool size while fixing all other pool sizes, and the same is almost true for CON. The AWB model with the lowest SOC is the best performing AWB model, while the CON model with the second lowest SOC is the best performing model. We observe that AWB displays more changes in slope sign and qualitatively displays more adaptive dynamics, which prevents AWB from being fully ruled out for
Dynamic Bayesian Network Modeling of the Interplay between EGFR and Hedgehog Signaling.
Fröhlich, Holger; Bahamondez, Gloria; Götschel, Frank; Korf, Ulrike
2015-01-01
Aberrant activation of sonic Hegdehog (SHH) signaling has been found to disrupt cellular differentiation in many human cancers and to increase proliferation. The SHH pathway is known to cross-talk with EGFR dependent signaling. Recent studies experimentally addressed this interplay in Daoy cells, which are presumable a model system for medulloblastoma, a highly malignant brain tumor that predominately occurs in children. Currently ongoing are several clinical trials for different solid cancers, which are designed to validate the clinical benefits of targeting the SHH in combination with other pathways. This has motivated us to investigate interactions between EGFR and SHH dependent signaling in greater depth. To our knowledge, there is no mathematical model describing the interplay between EGFR and SHH dependent signaling in medulloblastoma so far. Here we come up with a fully probabilistic approach using Dynamic Bayesian Networks (DBNs). To build our model, we made use of literature based knowledge describing SHH and EGFR signaling and integrated gene expression (Illumina) and cellular location dependent time series protein expression data (Reverse Phase Protein Arrays). We validated our model by sub-sampling training data and making Bayesian predictions on the left out test data. Our predictions focusing on key transcription factors and p70S6K, showed a high level of concordance with experimental data. Furthermore, the stability of our model was tested by a parametric bootstrap approach. Stable network features were in agreement with published data. Altogether we believe that our model improved our understanding of the interplay between two highly oncogenic signaling pathways in Daoy cells. This may open new perspectives for the future therapy of Hedghog/EGF-dependent solid tumors.
Cortical electrophysiological network dynamics of feedback learning
Cohen, M.X.; Wilmes, K.A.; van de Vijver, I.
2011-01-01
Understanding the neurophysiological mechanisms of learning is important for both fundamental and clinical neuroscience. We present a neurophysiologically inspired framework for understanding cortical mechanisms of feedback-guided learning. This framework is based on dynamic changes in systems-level
Duggento, Andrea; Stankovski, Tomislav; McClintock, Peter V. E.; Stefanovska, Aneta
2012-12-01
Living systems have time-evolving interactions that, until recently, could not be identified accurately from recorded time series in the presence of noise. Stankovski [Phys. Rev. Lett.PRLTAO0031-900710.1103/PhysRevLett.109.024101 109, 024101 (2012)] introduced a method based on dynamical Bayesian inference that facilitates the simultaneous detection of time-varying synchronization, directionality of influence, and coupling functions. It can distinguish unsynchronized dynamics from noise-induced phase slips. The method is based on phase dynamics, with Bayesian inference of the time-evolving parameters being achieved by shaping the prior densities to incorporate knowledge of previous samples. We now present the method in detail using numerically generated data, data from an analog electronic circuit, and cardiorespiratory data. We also generalize the method to encompass networks of interacting oscillators and thus demonstrate its applicability to small-scale networks.
Risk-based reconfiguration of safety monitoring system using dynamic Bayesian network
International Nuclear Information System (INIS)
Kohda, Takehisa; Cui Weimin
2007-01-01
To prevent an abnormal event from leading to an accident, the role of its safety monitoring system is very important. The safety monitoring system detects symptoms of an abnormal event to mitigate its effect at its early stage. As the operation time passes by, the sensor reliability decreases, which implies that the decision criteria of the safety monitoring system should be modified depending on the sensor reliability as well as the system reliability. This paper presents a framework for the decision criteria (or diagnosis logic) of the safety monitoring system. The logic can be dynamically modified based on sensor output data monitored at regular intervals to minimize the expected loss caused by two types of safety monitoring system failure events: failed-dangerous (FD) and failed-safe (FS). The former corresponds to no response under an abnormal system condition, while the latter implies a spurious activation under a normal system condition. Dynamic Bayesian network theory can be applied to modeling the entire system behavior composed of the system and its safety monitoring system. Using the estimated state probabilities, the optimal decision criterion is given to obtain the optimal diagnosis logic. An illustrative example of a three-sensor system shows the merits and characteristics of the proposed method, where the reasonable interpretation of sensor data can be obtained
Identifying Key Drivers of Return Reversal with Dynamical Bayesian Factor Graph.
Directory of Open Access Journals (Sweden)
Shuai Zhao
Full Text Available In the stock market, return reversal occurs when investors sell overbought stocks and buy oversold stocks, reversing the stocks' price trends. In this paper, we develop a new method to identify key drivers of return reversal by incorporating a comprehensive set of factors derived from different economic theories into one unified dynamical Bayesian factor graph. We then use the model to depict factor relationships and their dynamics, from which we make some interesting discoveries about the mechanism behind return reversals. Through extensive experiments on the US stock market, we conclude that among the various factors, the liquidity factors consistently emerge as key drivers of return reversal, which is in support of the theory of liquidity effect. Specifically, we find that stocks with high turnover rates or high Amihud illiquidity measures have a greater probability of experiencing return reversals. Apart from the consistent drivers, we find other drivers of return reversal that generally change from year to year, and they serve as important characteristics for evaluating the trends of stock returns. Besides, we also identify some seldom discussed yet enlightening inter-factor relationships, one of which shows that stocks in Finance and Insurance industry are more likely to have high Amihud illiquidity measures in comparison with those in other industries. These conclusions are robust for return reversals under different thresholds.
Kourou, Konstantina; Papaloukas, Costas; Fotiadis, Dimitrios I
2017-03-01
Oral squamous cell carcinoma has been characterized as a complex disease which involves dynamic genomic changes at the molecular level. These changes indicate the worth to explore the interactions of the molecules and especially of differentially expressed genes that contribute to cancer progression. Moreover, based on this knowledge the identification of differentially expressed genes and related molecular pathways is of great importance. In the present study, we exploit differentially expressed genes in order to further perform pathway enrichment analysis. According to our results we found significant pathways in which the disease associated genes have been identified as strongly enriched. Furthermore, based on the results of the pathway enrichment analysis we propose a methodology for predicting oral cancer recurrence using dynamic Bayesian networks. The methodology takes into consideration time series gene expression data in order to predict a disease recurrence. Subsequently, we are able to conjecture about the causal interactions between genes in consecutive time intervals. Concerning the performance of the predictive models, the overall accuracy of the algorithm is 81.8% and the area under the ROC curve 89.2% regarding the knowledge from the overrepresented pre-NOTCH Expression and processing pathway.
Reconceptualizing Learning as a Dynamical System.
Ennis, Catherine D.
1992-01-01
Dynamical systems theory can increase our understanding of the constantly evolving learning process. Current research using experimental and interpretive paradigms focuses on describing the attractors and constraints stabilizing the educational process. Dynamical systems theory focuses attention on critical junctures in the learning process as…
Switching dynamics of multi-agent learning
Vrancx, P.; Tuyls, K.P.; Westra, R.
2008-01-01
This paper presents the dynamics of multi-agent reinforcement learning in multiple state problems. We extend previous work that formally modelled the relation between reinforcement learning agents and replicator dynamics in stateless multi-agent games. More precisely, in this work we use a
DRABAL: novel method to mine large high-throughput screening assays using Bayesian active learning
Soufan, Othman
2016-11-10
Background Mining high-throughput screening (HTS) assays is key for enhancing decisions in the area of drug repositioning and drug discovery. However, many challenges are encountered in the process of developing suitable and accurate methods for extracting useful information from these assays. Virtual screening and a wide variety of databases, methods and solutions proposed to-date, did not completely overcome these challenges. This study is based on a multi-label classification (MLC) technique for modeling correlations between several HTS assays, meaning that a single prediction represents a subset of assigned correlated labels instead of one label. Thus, the devised method provides an increased probability for more accurate predictions of compounds that were not tested in particular assays. Results Here we present DRABAL, a novel MLC solution that incorporates structure learning of a Bayesian network as a step to model dependency between the HTS assays. In this study, DRABAL was used to process more than 1.4 million interactions of over 400,000 compounds and analyze the existing relationships between five large HTS assays from the PubChem BioAssay Database. Compared to different MLC methods, DRABAL significantly improves the F1Score by about 22%, on average. We further illustrated usefulness and utility of DRABAL through screening FDA approved drugs and reported ones that have a high probability to interact with several targets, thus enabling drug-multi-target repositioning. Specifically DRABAL suggests the Thiabendazole drug as a common activator of the NCP1 and Rab-9A proteins, both of which are designed to identify treatment modalities for the Niemann–Pick type C disease. Conclusion We developed a novel MLC solution based on a Bayesian active learning framework to overcome the challenge of lacking fully labeled training data and exploit actual dependencies between the HTS assays. The solution is motivated by the need to model dependencies between existing
Novel dynamic Bayesian networks for facial action element recognition and understanding
Zhao, Wei; Park, Jeong-Seon; Choi, Dong-You; Lee, Sang-Woong
2011-12-01
In daily life, language is an important tool of communication between people. Besides language, facial action can also provide a great amount of information. Therefore, facial action recognition has become a popular research topic in the field of human-computer interaction (HCI). However, facial action recognition is quite a challenging task due to its complexity. In a literal sense, there are thousands of facial muscular movements, many of which have very subtle differences. Moreover, muscular movements always occur simultaneously when the pose is changed. To address this problem, we first build a fully automatic facial points detection system based on a local Gabor filter bank and principal component analysis. Then, novel dynamic Bayesian networks are proposed to perform facial action recognition using the junction tree algorithm over a limited number of feature points. In order to evaluate the proposed method, we have used the Korean face database for model training. For testing, we used the CUbiC FacePix, facial expressions and emotion database, Japanese female facial expression database, and our own database. Our experimental results clearly demonstrate the feasibility of the proposed approach.
Directory of Open Access Journals (Sweden)
Raffi Tonikian
2009-10-01
Full Text Available SH3 domains are peptide recognition modules that mediate the assembly of diverse biological complexes. We scanned billions of phage-displayed peptides to map the binding specificities of the SH3 domain family in the budding yeast, Saccharomyces cerevisiae. Although most of the SH3 domains fall into the canonical classes I and II, each domain utilizes distinct features of its cognate ligands to achieve binding selectivity. Furthermore, we uncovered several SH3 domains with specificity profiles that clearly deviate from the two canonical classes. In conjunction with phage display, we used yeast two-hybrid and peptide array screening to independently identify SH3 domain binding partners. The results from the three complementary techniques were integrated using a Bayesian algorithm to generate a high-confidence yeast SH3 domain interaction map. The interaction map was enriched for proteins involved in endocytosis, revealing a set of SH3-mediated interactions that underlie formation of protein complexes essential to this biological pathway. We used the SH3 domain interaction network to predict the dynamic localization of several previously uncharacterized endocytic proteins, and our analysis suggests a novel role for the SH3 domains of Lsb3p and Lsb4p as hubs that recruit and assemble several endocytic complexes.
Application of Dynamic naïve Bayesian classifier to comprehensive drought assessment
Park, D. H.; Lee, J. Y.; Lee, J. H.; KIm, T. W.
2017-12-01
Drought monitoring has already been extensively studied due to the widespread impacts and complex causes of drought. The most important component of drought monitoring is to estimate the characteristics and extent of drought by quantitatively measuring the characteristics of drought. Drought assessment considering different aspects of the complicated drought condition and uncertainty of drought index is great significance in accurate drought monitoring. This study used the dynamic Naïve Bayesian Classifier (DNBC) which is an extension of the Hidden Markov Model (HMM), to model and classify drought by using various drought indices for integrated drought assessment. To provide a stable model for combined use of multiple drought indices, this study employed the DNBC to perform multi-index drought assessment by aggregating the effect of different type of drought and considering the inherent uncertainty. Drought classification was performed by the DNBC using several drought indices: Standardized Precipitation Index (SPI), Streamflow Drought Index (SDI), and Normalized Vegetation Supply Water Index (NVSWI)) that reflect meteorological, hydrological, and agricultural drought characteristics. Overall results showed that in comparison unidirectional (SPI, SDI, and NVSWI) or multivariate (Composite Drought Index, CDI) drought assessment, the proposed DNBC was able to synthetically classify of drought considering uncertainty. Model provided method for comprehensive drought assessment with combined use of different drought indices.
Onisko, Agnieszka; Druzdzel, Marek J; Austin, R Marshall
2016-01-01
Classical statistics is a well-established approach in the analysis of medical data. While the medical community seems to be familiar with the concept of a statistical analysis and its interpretation, the Bayesian approach, argued by many of its proponents to be superior to the classical frequentist approach, is still not well-recognized in the analysis of medical data. The goal of this study is to encourage data analysts to use the Bayesian approach, such as modeling with graphical probabilistic networks, as an insightful alternative to classical statistical analysis of medical data. This paper offers a comparison of two approaches to analysis of medical time series data: (1) classical statistical approach, such as the Kaplan-Meier estimator and the Cox proportional hazards regression model, and (2) dynamic Bayesian network modeling. Our comparison is based on time series cervical cancer screening data collected at Magee-Womens Hospital, University of Pittsburgh Medical Center over 10 years. The main outcomes of our comparison are cervical cancer risk assessments produced by the three approaches. However, our analysis discusses also several aspects of the comparison, such as modeling assumptions, model building, dealing with incomplete data, individualized risk assessment, results interpretation, and model validation. Our study shows that the Bayesian approach is (1) much more flexible in terms of modeling effort, and (2) it offers an individualized risk assessment, which is more cumbersome for classical statistical approaches.
Liao, Stephen Shaoyi; Wang, Huai Qing; Li, Qiu Dan; Liu, Wei Yi
2006-06-01
This paper presents a new method for learning Bayesian networks from functional dependencies (FD) and third normal form (3NF) tables in relational databases. The method sets up a linkage between the theory of relational databases and probabilistic reasoning models, which is interesting and useful especially when data are incomplete and inaccurate. The effectiveness and practicability of the proposed method is demonstrated by its implementation in a mobile commerce system.
Bayesian network representing system dynamics in risk analysis of nuclear systems
Varuttamaseni, Athi
2011-12-01
A dynamic Bayesian network (DBN) model is used in conjunction with the alternating conditional expectation (ACE) regression method to analyze the risk associated with the loss of feedwater accident coupled with a subsequent initiation of the feed and bleed operation in the Zion-1 nuclear power plant. The use of the DBN allows the joint probability distribution to be factorized, enabling the analysis to be done on many simpler network structures rather than on one complicated structure. The construction of the DBN model assumes conditional independence relations among certain key reactor parameters. The choice of parameter to model is based on considerations of the macroscopic balance statements governing the behavior of the reactor under a quasi-static assumption. The DBN is used to relate the peak clad temperature to a set of independent variables that are known to be important in determining the success of the feed and bleed operation. A simple linear relationship is then used to relate the clad temperature to the core damage probability. To obtain a quantitative relationship among different nodes in the DBN, surrogates of the RELAP5 reactor transient analysis code are used. These surrogates are generated by applying the ACE algorithm to output data obtained from about 50 RELAP5 cases covering a wide range of the selected independent variables. These surrogates allow important safety parameters such as the fuel clad temperature to be expressed as a function of key reactor parameters such as the coolant temperature and pressure together with important independent variables such as the scram delay time. The time-dependent core damage probability is calculated by sampling the independent variables from their probability distributions and propagate the information up through the Bayesian network to give the clad temperature. With the knowledge of the clad temperature and the assumption that the core damage probability has a one-to-one relationship to it, we have
A Dynamic Bayesian Model for Characterizing Cross-Neuronal Interactions During Decision-Making.
Zhou, Bo; Moorman, David E; Behseta, Sam; Ombao, Hernando; Shahbaba, Babak
2016-01-01
The goal of this paper is to develop a novel statistical model for studying cross-neuronal spike train interactions during decision making. For an individual to successfully complete the task of decision-making, a number of temporally-organized events must occur: stimuli must be detected, potential outcomes must be evaluated, behaviors must be executed or inhibited, and outcomes (such as reward or no-reward) must be experienced. Due to the complexity of this process, it is likely the case that decision-making is encoded by the temporally-precise interactions between large populations of neurons. Most existing statistical models, however, are inadequate for analyzing such a phenomenon because they provide only an aggregated measure of interactions over time. To address this considerable limitation, we propose a dynamic Bayesian model which captures the time-varying nature of neuronal activity (such as the time-varying strength of the interactions between neurons). The proposed method yielded results that reveal new insight into the dynamic nature of population coding in the prefrontal cortex during decision making. In our analysis, we note that while some neurons in the prefrontal cortex do not synchronize their firing activity until the presence of a reward, a different set of neurons synchronize their activity shortly after stimulus onset. These differentially synchronizing sub-populations of neurons suggests a continuum of population representation of the reward-seeking task. Secondly, our analyses also suggest that the degree of synchronization differs between the rewarded and non-rewarded conditions. Moreover, the proposed model is scalable to handle data on many simultaneously-recorded neurons and is applicable to analyzing other types of multivariate time series data with latent structure. Supplementary materials (including computer codes) for our paper are available online.
International Nuclear Information System (INIS)
Argentiero, Amedeo; Bovi, Maurizio; Cerqueti, Roy
2016-01-01
This paper examines psycho-induced overconsumption in a dynamic stochastic context. As emphasized by well-established psychological results, these psycho-distortions derive from a decision making based on simple rules-of-thumb, not on analytically sounded optimizations. To our end, we therefore compare two New Keynesian models. The first is populated by optimizing Muth-rational agents and acts as the normative benchmark. The other is a “psycho-perturbed” version of the benchmark that allows for the potential presence of overoptimism and, hence, of overconsumption. The parameters of these models are estimated through a Bayesian-type procedure, and performances are evaluated by employing an entropy measure. Such methodologies are particularly appropriate here since they take in full consideration the complexity generated by the randomness of the considered systems. In particular, they let to derive a not negligible information on the size and on the cyclical properties of the biases. In line with cognitive psychology suggestions our evidence shows that the overoptimism/overconsumption is: widespread—it is detected in nation-wide data; persistent—it emerges in full-sample estimations; it moves according to the expected cyclical behavior—larger in booms, and it disappears in crises. Moreover, by taking into account the effect of these psycho-biases, the model fits actual data better than the benchmark. All considered, then, enhancing the existing literature our findings: i) sustain the importance of inserting psychological distortions in macroeconomic models and ii) underline that system dynamics and psycho biases have statistically significant and economically important connections.
A bayesian approach for learning and tracking switching, non-stationary opponents
CSIR Research Space (South Africa)
Hernandez-Leal, P
2016-02-01
Full Text Available of interactions. We propose using a Bayesian framework to address this problem. Bayesian policy reuse (BPR) has been empirically shown to be efficient at correctly detecting the best policy to use from a library in sequential decision tasks. In this paper we...
Sparse Bayesian learning machine for real-time management of reservoir releases
Khalil, Abedalrazq; McKee, Mac; Kemblowski, Mariush; Asefa, Tirusew
2005-11-01
Water scarcity and uncertainties in forecasting future water availabilities present serious problems for basin-scale water management. These problems create a need for intelligent prediction models that learn and adapt to their environment in order to provide water managers with decision-relevant information related to the operation of river systems. This manuscript presents examples of state-of-the-art techniques for forecasting that combine excellent generalization properties and sparse representation within a Bayesian paradigm. The techniques are demonstrated as decision tools to enhance real-time water management. A relevance vector machine, which is a probabilistic model, has been used in an online fashion to provide confident forecasts given knowledge of some state and exogenous conditions. In practical applications, online algorithms should recognize changes in the input space and account for drift in system behavior. Support vectors machines lend themselves particularly well to the detection of drift and hence to the initiation of adaptation in response to a recognized shift in system structure. The resulting model will normally have a structure and parameterization that suits the information content of the available data. The utility and practicality of this proposed approach have been demonstrated with an application in a real case study involving real-time operation of a reservoir in a river basin in southern Utah.
He, Xingyu; Tong, Ningning; Hu, Xiaowei
2018-01-01
Compressive sensing has been successfully applied to inverse synthetic aperture radar (ISAR) imaging of moving targets. By exploiting the block sparse structure of the target image, sparse solution for multiple measurement vectors (MMV) can be applied in ISAR imaging and a substantial performance improvement can be achieved. As an effective sparse recovery method, sparse Bayesian learning (SBL) for MMV involves a matrix inverse at each iteration. Its associated computational complexity grows significantly with the problem size. To address this problem, we develop a fast inverse-free (IF) SBL method for MMV. A relaxed evidence lower bound (ELBO), which is computationally more amiable than the traditional ELBO used by SBL, is obtained by invoking fundamental property for smooth functions. A variational expectation-maximization scheme is then employed to maximize the relaxed ELBO, and a computationally efficient IF-MSBL algorithm is proposed. Numerical results based on simulated and real data show that the proposed method can reconstruct row sparse signal accurately and obtain clear superresolution ISAR images. Moreover, the running time and computational complexity are reduced to a great extent compared with traditional SBL methods.
Grzegorczyk, Marco; Husmeier, Dirk
2012-07-12
An important and challenging problem in systems biology is the inference of gene regulatory networks from short non-stationary time series of transcriptional profiles. A popular approach that has been widely applied to this end is based on dynamic Bayesian networks (DBNs), although traditional homogeneous DBNs fail to model the non-stationarity and time-varying nature of the gene regulatory processes. Various authors have therefore recently proposed combining DBNs with multiple changepoint processes to obtain time varying dynamic Bayesian networks (TV-DBNs). However, TV-DBNs are not without problems. Gene expression time series are typically short, which leaves the model over-flexible, leading to over-fitting or inflated inference uncertainty. In the present paper, we introduce a Bayesian regularization scheme that addresses this difficulty. Our approach is based on the rationale that changes in gene regulatory processes appear gradually during an organism's life cycle or in response to a changing environment, and we have integrated this notion in the prior distribution of the TV-DBN parameters. We have extensively tested our regularized TV-DBN model on synthetic data, in which we have simulated short non-homogeneous time series produced from a system subject to gradual change. We have then applied our method to real-world gene expression time series, measured during the life cycle of Drosophila melanogaster, under artificially generated constant light condition in Arabidopsis thaliana, and from a synthetically designed strain of Saccharomyces cerevisiae exposed to a changing environment.
Maeda, Shin-ichi
2014-01-01
Dropout is one of the key techniques to prevent the learning from overfitting. It is explained that dropout works as a kind of modified L2 regularization. Here, we shed light on the dropout from Bayesian standpoint. Bayesian interpretation enables us to optimize the dropout rate, which is beneficial for learning of weight parameters and prediction after learning. The experiment result also encourages the optimization of the dropout.
Directory of Open Access Journals (Sweden)
Marco Scutari
2017-03-01
Full Text Available It is well known in the literature that the problem of learning the structure of Bayesian networks is very hard to tackle: Its computational complexity is super-exponential in the number of nodes in the worst case and polynomial in most real-world scenarios. Efficient implementations of score-based structure learning benefit from past and current research in optimization theory, which can be adapted to the task by using the network score as the objective function to maximize. This is not true for approaches based on conditional independence tests, called constraint-based learning algorithms. The only optimization in widespread use, backtracking, leverages the symmetries implied by the definitions of neighborhood and Markov blanket. In this paper we illustrate how backtracking is implemented in recent versions of the bnlearn R package, and how it degrades the stability of Bayesian network structure learning for little gain in terms of speed. As an alternative, we describe a software architecture and framework that can be used to parallelize constraint-based structure learning algorithms (also implemented in bnlearn and we demonstrate its performance using four reference networks and two real-world data sets from genetics and systems biology. We show that on modern multi-core or multiprocessor hardware parallel implementations are preferable over backtracking, which was developed when single-processor machines were the norm.
Bayesian analysis of the dynamic cosmic web in the SDSS galaxy survey
International Nuclear Information System (INIS)
Leclercq, Florent; Wandelt, Benjamin; Jasche, Jens
2015-01-01
Recent application of the Bayesian algorithm \\textsc(borg) to the Sloan Digital Sky Survey (SDSS) main sample galaxies resulted in the physical inference of the formation history of the observed large-scale structure from its origin to the present epoch. In this work, we use these inferences as inputs for a detailed probabilistic cosmic web-type analysis. To do so, we generate a large set of data-constrained realizations of the large-scale structure using a fast, fully non-linear gravitational model. We then perform a dynamic classification of the cosmic web into four distinct components (voids, sheets, filaments, and clusters) on the basis of the tidal field. Our inference framework automatically and self-consistently propagates typical observational uncertainties to web-type classification. As a result, this study produces accurate cosmographic classification of large-scale structure elements in the SDSS volume. By also providing the history of these structure maps, the approach allows an analysis of the origin and growth of the early traces of the cosmic web present in the initial density field and of the evolution of global quantities such as the volume and mass filling fractions of different structures. For the problem of web-type classification, the results described in this work constitute the first connection between theory and observations at non-linear scales including a physical model of structure formation and the demonstrated capability of uncertainty quantification. A connection between cosmology and information theory using real data also naturally emerges from our probabilistic approach. Our results constitute quantitative chrono-cosmography of the complex web-like patterns underlying the observed galaxy distribution
On equivalent parameter learning in simplified feature space based on Bayesian asymptotic analysis.
Yamazaki, Keisuke
2012-07-01
Parametric models for sequential data, such as hidden Markov models, stochastic context-free grammars, and linear dynamical systems, are widely used in time-series analysis and structural data analysis. Computation of the likelihood function is one of primary considerations in many learning methods. Iterative calculation of the likelihood such as the model selection is still time-consuming though there are effective algorithms based on dynamic programming. The present paper studies parameter learning in a simplified feature space to reduce the computational cost. Simplifying data is a common technique seen in feature selection and dimension reduction though an oversimplified space causes adverse learning results. Therefore, we mathematically investigate a condition of the feature map to have an asymptotically equivalent convergence point of estimated parameters, referred to as the vicarious map. As a demonstration to find vicarious maps, we consider the feature space, which limits the length of data, and derive a necessary length for parameter learning in hidden Markov models. Copyright © 2012 Elsevier Ltd. All rights reserved.
Learning Dynamics in Doctoral Supervision
DEFF Research Database (Denmark)
Kobayashi, Sofie
investigates learning opportunities in supervision with multiple supervisors. This was investigated through observations and recording of supervision, and subsequent analysis of transcripts. The analyses used different perspectives on learning; learning as participation, positioning theory and variation theory....... The research illuminates how learning opportunities are created in the interaction through the scientific discussions. It also shows how multiple supervisors can contribute to supervision by providing new perspectives and opinions that have a potential for creating new understandings. The combination...... of different theoretical frameworks from the perspectives of learning as individual acquisition and a sociocultural perspective on learning contributed to a nuanced illustration of the otherwise implicit practices of supervision....
Gweon, Gey-Hong; Lee, Hee-Sun; Dorsey, Chad; Tinker, Robert; Finzer, William; Damelin, Daniel
2015-03-01
In tracking student learning in on-line learning systems, the Bayesian knowledge tracing (BKT) model is a popular model. However, the model has well-known problems such as the identifiability problem or the empirical degeneracy problem. Understanding of these problems remain unclear and solutions to them remain subjective. Here, we analyze the log data from an online physics learning program with our new model, a Monte Carlo BKT model. With our new approach, we are able to perform a completely unbiased analysis, which can then be used for classifying student learning patterns and performances. Furthermore, a theoretical analysis of the BKT model and our computational work shed new light on the nature of the aforementioned problems. This material is based upon work supported by the National Science Foundation under Grant REC-1147621 and REC-1435470.
Energy Technology Data Exchange (ETDEWEB)
Zhao, Yunfei; Tong, Jiejuan; Zhang, Liguo, E-mail: lgzhang@tsinghua.edu.cn; Zhang, Qin
2015-09-15
Highlights: • Dynamic Bayesian network is used to diagnose and predict accident progress in HTR-PM. • Dynamic Bayesian network model of HTR-PM is built based on detailed system analysis. • LOCA Simulations validate the above model even if part monitors are lost or false. - Abstract: The first high-temperature-reactor pebble-bed demonstration module (HTR-PM) is under construction currently in China. At the same time, development of a system that is used to support nuclear emergency response is in progress. The supporting system is expected to complete two tasks. The first one is diagnostics of the fault in the reactor based on abnormal sensor measurements obtained. The second one is prognostic of the accident progression based on sensor measurements obtained and operator actions. Both tasks will provide valuable guidance for emergency staff to take appropriate protective actions. Traditional method for the two tasks relies heavily on expert judgment, and has been proven to be inappropriate in some cases, such as Three Mile Island accident. To better perform the two tasks, dynamic Bayesian networks (DBN) is introduced in this paper and a pilot study based on the approach is carried out. DBN is advantageous in representing complex dynamic systems and taking full consideration of evidences obtained to perform diagnostics and prognostics. Pearl's loopy belief propagation (LBP) algorithm is recommended for diagnostics and prognostics in DBN. The DBN model of HTR-PM is created based on detailed system analysis and accident progression analysis. A small break loss of coolant accident (SBLOCA) is selected to illustrate the application of the DBN model of HTR-PM in fault diagnostics (FD) and accident progression prognostics (APP). Several advantages of DBN approach compared with other techniques are discussed. The pilot study lays the foundation for developing the nuclear emergency response supporting system (NERSS) for HTR-PM.
Directory of Open Access Journals (Sweden)
Lei Guo
2017-02-01
Full Text Available Point-of-interest (POI recommendation has been well studied in recent years. However, most of the existing methods focus on the recommendation scenarios where users can provide explicit feedback. In most cases, however, the feedback is not explicit, but implicit. For example, we can only get a user’s check-in behaviors from the history of what POIs she/he has visited, but never know how much she/he likes and why she/he does not like them. Recently, some researchers have noticed this problem and began to learn the user preferences from the partial order of POIs. However, these works give equal weight to each POI pair and cannot distinguish the contributions from different POI pairs. Intuitively, for the two POIs in a POI pair, the larger the frequency difference of being visited and the farther the geographical distance between them, the higher the contribution of this POI pair to the ranking function. Based on the above observations, we propose a weighted ranking method for POI recommendation. Specifically, we first introduce a Bayesian personalized ranking criterion designed for implicit feedback to POI recommendation. To fully utilize the partial order of POIs, we then treat the cost function in a weighted way, that is give each POI pair a different weight according to their frequency of being visited and the geographical distance between them. Data analysis and experimental results on two real-world datasets demonstrate the existence of user preference on different POI pairs and the effectiveness of our weighted ranking method.
Improved Membership Probability for Moving Groups: Bayesian and Machine Learning Approaches
Lee, Jinhee; Song, Inseok
2018-01-01
Gravitationally unbound loose stellar associations (i.e., young nearby moving groups: moving groups hereafter) have been intensively explored because they are important in planet and disk formation studies, exoplanet imaging, and age calibration. Among the many efforts devoted to the search for moving group members, a Bayesian approach (e.g.,using the code BANYAN) has become popular recently because of the many advantages it offers. However, the resultant membership probability needs to be carefully adopted because of its sensitive dependence on input models. In this study, we have developed an improved membership calculation tool focusing on the beta-Pic moving group. We made three improvements for building models used in BANYAN II: (1) updating a list of accepted members by re-assessing memberships in terms of position, motion, and age, (2) investigating member distribution functions in XYZ, and (3) exploring field star distribution functions in XYZUVW. Our improved tool can change membership probability up to 70%. Membership probability is critical and must be better defined. For example, our code identifies only one third of the candidate members in SIMBAD that are believed to be kinematically associated with beta-Pic moving group.Additionally, we performed cluster analysis of young nearby stars using an unsupervised machine learning approach. As more moving groups and their members are identified, the complexity and ambiguity in moving group configuration has been increased. To clarify this issue, we analyzed ~4,000 X-ray bright young stellar candidates. Here, we present the preliminary results. By re-identifying moving groups with the least human intervention, we expect to understand the composition of the solar neighborhood. Moreover better defined moving group membership will help us understand star formation and evolution in relatively low density environments; especially for the low-mass stars which will be identified in the coming Gaia release.
Gopalan, Giri; Hrafnkelsson, Birgir; Aðalgeirsdóttir, Guðfinna; Jarosch, Alexander H.; Pálsson, Finnur
2018-03-01
Bayesian hierarchical modeling can assist the study of glacial dynamics and ice flow properties. This approach will allow glaciologists to make fully probabilistic predictions for the thickness of a glacier at unobserved spatio-temporal coordinates, and it will also allow for the derivation of posterior probability distributions for key physical parameters such as ice viscosity and basal sliding. The goal of this paper is to develop a proof of concept for a Bayesian hierarchical model constructed, which uses exact analytical solutions for the shallow ice approximation (SIA) introduced by Bueler et al. (2005). A suite of test simulations utilizing these exact solutions suggests that this approach is able to adequately model numerical errors and produce useful physical parameter posterior distributions and predictions. A byproduct of the development of the Bayesian hierarchical model is the derivation of a novel finite difference method for solving the SIA partial differential equation (PDE). An additional novelty of this work is the correction of numerical errors induced through a numerical solution using a statistical model. This error correcting process models numerical errors that accumulate forward in time and spatial variation of numerical errors between the dome, interior, and margin of a glacier.
Suboptimal Criterion Learning in Static and Dynamic Environments.
Directory of Open Access Journals (Sweden)
Elyse H Norton
2017-01-01
Full Text Available Humans often make decisions based on uncertain sensory information. Signal detection theory (SDT describes detection and discrimination decisions as a comparison of stimulus "strength" to a fixed decision criterion. However, recent research suggests that current responses depend on the recent history of stimuli and previous responses, suggesting that the decision criterion is updated trial-by-trial. The mechanisms underpinning criterion setting remain unknown. Here, we examine how observers learn to set a decision criterion in an orientation-discrimination task under both static and dynamic conditions. To investigate mechanisms underlying trial-by-trial criterion placement, we introduce a novel task in which participants explicitly set the criterion, and compare it to a more traditional discrimination task, allowing us to model this explicit indication of criterion dynamics. In each task, stimuli were ellipses with principal orientations drawn from two categories: Gaussian distributions with different means and equal variance. In the covert-criterion task, observers categorized a displayed ellipse. In the overt-criterion task, observers adjusted the orientation of a line that served as the discrimination criterion for a subsequently presented ellipse. We compared performance to the ideal Bayesian learner and several suboptimal models that varied in both computational and memory demands. Under static and dynamic conditions, we found that, in both tasks, observers used suboptimal learning rules. In most conditions, a model in which the recent history of past samples determines a belief about category means fit the data best for most observers and on average. Our results reveal dynamic adjustment of discrimination criterion, even after prolonged training, and indicate how decision criteria are updated over time.
Distance learning, problem based learning and dynamic knowledge networks.
Giani, U; Martone, P
1998-06-01
This paper is an attempt to develop a distance learning model grounded upon a strict integration of problem based learning (PBL), dynamic knowledge networks (DKN) and web tools, such as hypermedia documents, synchronous and asynchronous communication facilities, etc. The main objective is to develop a theory of distance learning based upon the idea that learning is a highly dynamic cognitive process aimed at connecting different concepts in a network of mutually supporting concepts. Moreover, this process is supposed to be the result of a social interaction that has to be facilitated by the web. The model was tested by creating a virtual classroom of medical and nursing students and activating a learning session on the concept of knowledge representation in health sciences.
Directory of Open Access Journals (Sweden)
Steven Matthew Thurman
2014-02-01
Full Text Available Visual form analysis is fundamental to shape perception and likely plays a central role in perception of more complex dynamic shapes, such as moving objects or biological motion. Two primary form-based cues serve to represent the overall shape of an object: the spatial position and the orientation of locations along the boundary of the object. However, it is unclear how the visual system integrates these two sources of information in dynamic form analysis, and in particular how the brain resolves ambiguities due to sensory uncertainty and/or cue conflict. In the current study, we created animations of sparsely-sampled dynamic objects (human walkers or rotating squares comprised of oriented Gabor patches in which orientation could either coincide or conflict with information provided by position cues. When the cues were incongruent, we found a characteristic trade-off between position and orientation information whereby position cues increasingly dominated perception as the relative uncertainty of orientation increased and vice versa. Furthermore, we found no evidence for differences in the visual processing of biological and non-biological objects, casting doubt on the claim that biological motion may be specialized in the human brain, at least in specific terms of form analysis. To explain these behavioral results quantitatively, we adopt a probabilistic template-matching model that uses Bayesian inference within local modules to estimate object shape separately from either spatial position or orientation signals. The outputs of the two modules are integrated with weights that reflect individual estimates of subjective cue reliability, and integrated over time to produce a decision about the perceived dynamics of the input data. Results of this model provided a close fit to the behavioral data, suggesting a mechanism in the human visual system that approximates rational Bayesian inference to integrate position and orientation signals in dynamic
Schall, Megan K.; Blazer, Vicki S.; Lorantas, Robert M.; Smith, Geoffrey; Mullican, John E.; Keplinger, Brandon J.; Wagner, Tyler
2018-01-01
Detecting temporal changes in fish abundance is an essential component of fisheries management. Because of the need to understand short‐term and nonlinear changes in fish abundance, traditional linear models may not provide adequate information for management decisions. This study highlights the utility of Bayesian dynamic linear models (DLMs) as a tool for quantifying temporal dynamics in fish abundance. To achieve this goal, we quantified temporal trends of Smallmouth Bass Micropterus dolomieu catch per effort (CPE) from rivers in the mid‐Atlantic states, and we calculated annual probabilities of decline from the posterior distributions of annual rates of change in CPE. We were interested in annual declines because of recent concerns about fish health in portions of the study area. In general, periods of decline were greatest within the Susquehanna River basin, Pennsylvania. The declines in CPE began in the late 1990s—prior to observations of fish health problems—and began to stabilize toward the end of the time series (2011). In contrast, many of the other rivers investigated did not have the same magnitude or duration of decline in CPE. Bayesian DLMs provide information about annual changes in abundance that can inform management and are easily communicated with managers and stakeholders.
Fröhlich, H.; Klau, G.W.
2013-01-01
Bayesian Networks are an established computational approach for data driven network inference. However, experimental data is limited in its availability and corrupted by noise. This leads to an unavoidable uncertainty about the correct network structure. Thus sampling or bootstrap based strategies
Directory of Open Access Journals (Sweden)
Qing Ye
2015-01-01
Full Text Available This research proposes a novel framework of final drive simultaneous failure diagnosis containing feature extraction, training paired diagnostic models, generating decision threshold, and recognizing simultaneous failure modes. In feature extraction module, adopt wavelet package transform and fuzzy entropy to reduce noise interference and extract representative features of failure mode. Use single failure sample to construct probability classifiers based on paired sparse Bayesian extreme learning machine which is trained only by single failure modes and have high generalization and sparsity of sparse Bayesian learning approach. To generate optimal decision threshold which can convert probability output obtained from classifiers into final simultaneous failure modes, this research proposes using samples containing both single and simultaneous failure modes and Grid search method which is superior to traditional techniques in global optimization. Compared with other frequently used diagnostic approaches based on support vector machine and probability neural networks, experiment results based on F1-measure value verify that the diagnostic accuracy and efficiency of the proposed framework which are crucial for simultaneous failure diagnosis are superior to the existing approach.
Approaches to Learning to Control Dynamic Uncertainty
Directory of Open Access Journals (Sweden)
Magda Osman
2015-10-01
Full Text Available In dynamic environments, when faced with a choice of which learning strategy to adopt, do people choose to mostly explore (maximizing their long term gains or exploit (maximizing their short term gains? More to the point, how does this choice of learning strategy influence one’s later ability to control the environment? In the present study, we explore whether people’s self-reported learning strategies and levels of arousal (i.e., surprise, stress correspond to performance measures of controlling a Highly Uncertain or Moderately Uncertain dynamic environment. Generally, self-reports suggest a preference for exploring the environment to begin with. After which, those in the Highly Uncertain environment generally indicated they exploited more than those in the Moderately Uncertain environment; this difference did not impact on performance on later tests of people’s ability to control the dynamic environment. Levels of arousal were also differentially associated with the uncertainty of the environment. Going beyond behavioral data, our model of dynamic decision-making revealed that, in actual fact, there was no difference in exploitation levels between those in the highly uncertain or moderately uncertain environments, but there were differences based on sensitivity to negative reinforcement. We consider the implications of our findings with respect to learning and strategic approaches to controlling dynamic uncertainty.
International Nuclear Information System (INIS)
Wong, Ka In; Wong, Pak Kin
2017-01-01
Highlights: • A new calibration method is proposed for dual-injection engines under biofuel blends. • Sparse Bayesian extreme learning machine and flower pollination algorithm are employed in the proposed method. • An SI engine is retrofitted for operating under dual-injection strategy. • The proposed method is verified experimentally under the two idle speed conditions. • Comparison with other machine learning methods and optimization algorithms is conducted. - Abstract: Although many combinations of biofuel blends are available in the market, it is more beneficial to vary the ratio of biofuel blends at different engine operating conditions for optimal engine performance. Dual-injection engines have the potential to implement such function. However, while optimal engine calibration is critical for achieving high performance, the use of two injection systems, together with other modern engine technologies, leads the calibration of the dual-injection engines to a very complicated task. Traditional trial-and-error-based calibration approach can no longer be adopted as it would be time-, fuel- and labor-consuming. Therefore, a new and fast calibration method based on sparse Bayesian extreme learning machine (SBELM) and metaheuristic optimization is proposed to optimize the dual-injection engines operating with biofuels. A dual-injection spark-ignition engine fueled with ethanol and gasoline is employed for demonstration purpose. The engine response for various parameters is firstly acquired, and an engine model is then constructed using SBELM. With the engine model, the optimal engine settings are determined based on recently proposed metaheuristic optimization methods. Experimental results validate the optimal settings obtained with the proposed methodology, indicating that the use of machine learning and metaheuristic optimization for dual-injection engine calibration is effective and promising.
Innovation, learning and cluster dynamics
B. Nooteboom (Bart)
2004-01-01
textabstractThis chapter offers a theory and method for the analysis of the dynamics, i.e. the development, of clusters for innovation. It employs an analysis of three types of embedding: institutional embedding, which is often localized, structural embedding (network structure), and relational
Learning dynamics in social dilemmas
Macy, MW; Flache, A; Macy, Michael W.
2002-01-01
The Nash equilibrium, the main solution concept in analytical game theory, cannot make precise predictions about the outcome of repeated mixed-motive games. Nor can it tell us much about the dynamics by which a population of players moves from one equilibrium to another. These limitations, along
SensibleSleep: A Bayesian Model for Learning Sleep Patterns from Smartphone Events
DEFF Research Database (Denmark)
Cuttone, Andrea; Bækgaard, Per; Sekara, Vedran
2017-01-01
We propose a Bayesian model for extracting sleep patterns from smartphone events. Our method is able to identify individuals' daily sleep periods and their evolution over time, and provides an estimation of the probability of sleep and wake transitions. The model is fitted to more than 400...... to quantify uncertainty and encode prior knowledge about sleep patterns. Compared with existing smartphone-based systems, our method requires only screen on/off events, and is therefore much less intrusive in terms of privacy and more battery-efficient....... participants from two different datasets, and we verify the results against ground truth from dedicated armband sleep trackers. We show that the model is able to produce reliable sleep estimates with an accuracy of 0.89, both at the individual and at the collective level. Moreover the Bayesian model is able...
SensibleSleep: A Bayesian Model for Learning Sleep Patterns from Smartphone Events.
Cuttone, Andrea; Bækgaard, Per; Sekara, Vedran; Jonsson, Håkan; Larsen, Jakob Eg; Lehmann, Sune
2017-01-01
We propose a Bayesian model for extracting sleep patterns from smartphone events. Our method is able to identify individuals' daily sleep periods and their evolution over time, and provides an estimation of the probability of sleep and wake transitions. The model is fitted to more than 400 participants from two different datasets, and we verify the results against ground truth from dedicated armband sleep trackers. We show that the model is able to produce reliable sleep estimates with an accuracy of 0.89, both at the individual and at the collective level. Moreover the Bayesian model is able to quantify uncertainty and encode prior knowledge about sleep patterns. Compared with existing smartphone-based systems, our method requires only screen on/off events, and is therefore much less intrusive in terms of privacy and more battery-efficient.
SensibleSleep: A Bayesian Model for Learning Sleep Patterns from Smartphone Events.
Directory of Open Access Journals (Sweden)
Andrea Cuttone
Full Text Available We propose a Bayesian model for extracting sleep patterns from smartphone events. Our method is able to identify individuals' daily sleep periods and their evolution over time, and provides an estimation of the probability of sleep and wake transitions. The model is fitted to more than 400 participants from two different datasets, and we verify the results against ground truth from dedicated armband sleep trackers. We show that the model is able to produce reliable sleep estimates with an accuracy of 0.89, both at the individual and at the collective level. Moreover the Bayesian model is able to quantify uncertainty and encode prior knowledge about sleep patterns. Compared with existing smartphone-based systems, our method requires only screen on/off events, and is therefore much less intrusive in terms of privacy and more battery-efficient.
Learning Consumer Tastes Through Dynamic Assortments
Ulu, C.; Honhon, D.B.L.P.; Alptekinoglu, A.
2012-01-01
How should a firm modify its product assortment over time when learning about consumer tastes? In this paper, we study dynamic assortment decisions in a horizontally differentiated product category for which consumers' diverse tastes can be represented as locations on a Hotelling line. We presume
Galbraith, Craig S.; Merrill, Gregory B.; Kline, Doug M.
2012-01-01
In this study we investigate the underlying relational structure between student evaluations of teaching effectiveness (SETEs) and achievement of student learning outcomes in 116 business related courses. Utilizing traditional statistical techniques, a neural network analysis and a Bayesian data reduction and classification algorithm, we find…
Seko, Atsuto; Togo, Atsushi; Hayashi, Hiroyuki; Tsuda, Koji; Chaput, Laurent; Tanaka, Isao
2015-11-01
Compounds of low lattice thermal conductivity (LTC) are essential for seeking thermoelectric materials with high conversion efficiency. Some strategies have been used to decrease LTC. However, such trials have yielded successes only within a limited exploration space. Here, we report the virtual screening of a library containing 54 779 compounds. Our strategy is to search the library through Bayesian optimization using for the initial data the LTC obtained from first-principles anharmonic lattice-dynamics calculations for a set of 101 compounds. We discovered 221 materials with very low LTC. Two of them even have an electronic band gap <1 eV , which makes them exceptional candidates for thermoelectric applications. In addition to those newly discovered thermoelectric materials, the present strategy is believed to be powerful for many other applications in which the chemistry of materials is required to be optimized.
CSIR Research Space (South Africa)
Rosman, Benjamin
2016-02-01
Full Text Available Keywords Policy Reuse · Reinforcement Learning · Online Learning · Online Bandits · Transfer Learning · Bayesian Optimisation · Bayesian Decision Theory. 1 Introduction As robots and software agents are becoming more ubiquitous in many applications.... The agent has access to a library of policies (pi1, pi2 and pi3), and has previously experienced a set of task instances (τ1, τ2, τ3, τ4), as well as samples of the utilities of the library policies on these instances (the black dots indicate the means...
Bayesian Network Induction via Local Neighborhoods
National Research Council Canada - National Science Library
Margaritis, Dimitris
1999-01-01
.... We present an efficient algorithm for learning Bayesian networks from data. Our approach constructs Bayesian networks by first identifying each node's Markov blankets, then connecting nodes in a consistent way...
SensibleSleep: A Bayesian Model for Learning Sleep Patterns from Smartphone Events
DEFF Research Database (Denmark)
Cuttone, Andrea; Bækgaard, Per; Sekara, Vedran
2017-01-01
We propose a Bayesian model for extracting sleep patterns from smartphone events. Our method is able to identify individuals' daily sleep periods and their evolution over time, and provides an estimation of the probability of sleep and wake transitions. The model is fitted to more than 400...... to quantify uncertainty and encode prior knowledge about sleep patterns. Compared with existing smartphone-based systems, our method requires only screen on/off events, and is therefore much less intrusive in terms of privacy and more battery-efficient....
Bayesian optimization for materials science
Packwood, Daniel
2017-01-01
This book provides a short and concise introduction to Bayesian optimization specifically for experimental and computational materials scientists. After explaining the basic idea behind Bayesian optimization and some applications to materials science in Chapter 1, the mathematical theory of Bayesian optimization is outlined in Chapter 2. Finally, Chapter 3 discusses an application of Bayesian optimization to a complicated structure optimization problem in computational surface science. Bayesian optimization is a promising global optimization technique that originates in the field of machine learning and is starting to gain attention in materials science. For the purpose of materials design, Bayesian optimization can be used to predict new materials with novel properties without extensive screening of candidate materials. For the purpose of computational materials science, Bayesian optimization can be incorporated into first-principles calculations to perform efficient, global structure optimizations. While re...
Plug & Play object oriented Bayesian networks
DEFF Research Database (Denmark)
Bangsø, Olav; Flores, J.; Jensen, Finn Verner
2003-01-01
been shown to be quite suitable for dynamic domains as well. However, processing object oriented Bayesian networks in practice does not take advantage of their modular structure. Normally the object oriented Bayesian network is transformed into a Bayesian network and, inference is performed...... dynamic domains. The communication needed between instances is achieved by means of a fill-in propagation scheme....
Directory of Open Access Journals (Sweden)
Yi Sun
2017-12-01
Full Text Available Bayesian network classifiers (BNCs have demonstrated competitive classification accuracy in a variety of real-world applications. However, it is error-prone for BNCs to discriminate among high-confidence labels. To address this issue, we propose the label-driven learning framework, which incorporates instance-based learning and ensemble learning. For each testing instance, high-confidence labels are first selected by a generalist classifier, e.g., the tree-augmented naive Bayes (TAN classifier. Then, by focusing on these labels, conditional mutual information is redefined to more precisely measure mutual dependence between attributes, thus leading to a refined generalist with a more reasonable network structure. To enable finer discrimination, an expert classifier is tailored for each high-confidence label. Finally, the predictions of the refined generalist and the experts are aggregated. We extend TAN to LTAN (Label-driven TAN by applying the proposed framework. Extensive experimental results demonstrate that LTAN delivers superior classification accuracy to not only several state-of-the-art single-structure BNCs but also some established ensemble BNCs at the expense of reasonable computation overhead.
Indirect learning control for nonlinear dynamical systems
Ryu, Yeong Soon; Longman, Richard W.
1993-01-01
In a previous paper, learning control algorithms were developed based on adaptive control ideas for linear time variant systems. The learning control methods were shown to have certain advantages over their adaptive control counterparts, such as the ability to produce zero tracking error in time varying systems, and the ability to eliminate repetitive disturbances. In recent years, certain adaptive control algorithms have been developed for multi-body dynamic systems such as robots, with global guaranteed convergence to zero tracking error for the nonlinear system euations. In this paper we study the relationship between such adaptive control methods designed for this specific class of nonlinear systems, and the learning control problem for such systems, seeking to converge to zero tracking error in following a specific command repeatedly, starting from the same initial conditions each time. The extension of these methods from the adaptive control problem to the learning control problem is seen to be trivial. The advantages and disadvantages of using learning control based on such adaptive control concepts for nonlinear systems, and the use of other currently available learning control algorithms are discussed.
Dynamic Learning Objects to Teach Java Programming Language
Narasimhamurthy, Uma; Al Shawkani, Khuloud
2010-01-01
This article describes a model for teaching Java Programming Language through Dynamic Learning Objects. The design of the learning objects was based on effective learning design principles to help students learn the complex topic of Java Programming. Visualization was also used to facilitate the learning of the concepts. (Contains 1 figure and 2…
Learning State Space Dynamics in Recurrent Networks
Simard, Patrice Yvon
Fully recurrent (asymmetrical) networks can be used to learn temporal trajectories. The network is unfolded in time, and backpropagation is used to train the weights. The presence of recurrent connections creates internal states in the system which vary as a function of time. The resulting dynamics can provide interesting additional computing power but learning is made more difficult by the existence of internal memories. This study first exhibits the properties of recurrent networks in terms of convergence when the internal states of the system are unknown. A new energy functional is provided to change the weights of the units in order to the control the stability of the fixed points of the network's dynamics. The power of the resultant algorithm is illustrated with the simulation of a content addressable memory. Next, the more general case of time trajectories on a recurrent network is studied. An application is proposed in which trajectories are generated to draw letters as a function of an input. In another application of recurrent systems, a neural network certain temporal properties observed in human callosally sectioned brains. Finally the proposed algorithm for stabilizing dynamics around fixed points is extended to one for stabilizing dynamics around time trajectories. Its effects are illustrated on a network which generates Lisajous curves.
Time-Varying Combinations of Bayesian Dynamic Models and Equity Momentum Strategies
N. Basturk (Nalan); S. Grassi (Stefano); L.F. Hoogerheide (Lennart); H.K. van Dijk (Herman)
2016-01-01
markdownabstractA novel dynamic asset-allocation approach is proposed where portfolios as well as portfolio strategies are updated at every decision period based on their past performance. For modeling, a general class of models is specified that combines a dynamic factor and a vector autoregressive
Bayesian Analysis for Dynamic Generalized Linear Latent Model with Application to Tree Survival Rate
Directory of Open Access Journals (Sweden)
Yu-sheng Cheng
2014-01-01
Full Text Available Logistic regression model is the most popular regression technique, available for modeling categorical data especially for dichotomous variables. Classic logistic regression model is typically used to interpret relationship between response variables and explanatory variables. However, in real applications, most data sets are collected in follow-up, which leads to the temporal correlation among the data. In order to characterize the different variables correlations, a new method about the latent variables is introduced in this study. At the same time, the latent variables about AR (1 model are used to depict time dependence. In the framework of Bayesian analysis, parameters estimates and statistical inferences are carried out via Gibbs sampler with Metropolis-Hastings (MH algorithm. Model comparison, based on the Bayes factor, and forecasting/smoothing of the survival rate of the tree are established. A simulation study is conducted to assess the performance of the proposed method and a pika data set is analyzed to illustrate the real application. Since Bayes factor approaches vary significantly, efficiency tests have been performed in order to decide which solution provides a better tool for the analysis of real relational data sets.
Fuster-Parra, P; García-Mas, A; Ponseti, F J; Leo, F M
2015-04-01
The purpose of this paper was to discover the relationships among 22 relevant psychological features in semi-professional football players in order to study team's performance and collective efficacy via a Bayesian network (BN). The paper includes optimization of team's performance and collective efficacy using intercausal reasoning pattern which constitutes a very common pattern in human reasoning. The BN is used to make inferences regarding our problem, and therefore we obtain some conclusions; among them: maximizing the team's performance causes a decrease in collective efficacy and when team's performance achieves the minimum value it causes an increase in moderate/high values of collective efficacy. Similarly, we may reason optimizing team collective efficacy instead. It also allows us to determine the features that have the strongest influence on performance and which on collective efficacy. From the BN two different coaching styles were differentiated taking into account the local Markov property: training leadership and autocratic leadership. Copyright © 2014 Elsevier B.V. All rights reserved.
Ekins, Sean; Madrid, Peter B; Sarker, Malabika; Li, Shao-Gang; Mittal, Nisha; Kumar, Pradeep; Wang, Xin; Stratton, Thomas P; Zimmerman, Matthew; Talcott, Carolyn; Bourbon, Pauline; Travers, Mike; Yadav, Maneesh; Freundlich, Joel S
2015-01-01
Integrated computational approaches for Mycobacterium tuberculosis (Mtb) are useful to identify new molecules that could lead to future tuberculosis (TB) drugs. Our approach uses information derived from the TBCyc pathway and genome database, the Collaborative Drug Discovery TB database combined with 3D pharmacophores and dual event Bayesian models of whole-cell activity and lack of cytotoxicity. We have prioritized a large number of molecules that may act as mimics of substrates and metabolites in the TB metabolome. We computationally searched over 200,000 commercial molecules using 66 pharmacophores based on substrates and metabolites from Mtb and further filtering with Bayesian models. We ultimately tested 110 compounds in vitro that resulted in two compounds of interest, BAS 04912643 and BAS 00623753 (MIC of 2.5 and 5 μg/mL, respectively). These molecules were used as a starting point for hit-to-lead optimization. The most promising class proved to be the quinoxaline di-N-oxides, evidenced by transcriptional profiling to induce mRNA level perturbations most closely resembling known protonophores. One of these, SRI58 exhibited an MIC = 1.25 μg/mL versus Mtb and a CC50 in Vero cells of >40 μg/mL, while featuring fair Caco-2 A-B permeability (2.3 x 10-6 cm/s), kinetic solubility (125 μM at pH 7.4 in PBS) and mouse metabolic stability (63.6% remaining after 1 h incubation with mouse liver microsomes). Despite demonstration of how a combined bioinformatics/cheminformatics approach afforded a small molecule with promising in vitro profiles, we found that SRI58 did not exhibit quantifiable blood levels in mice.
Tang, Niansheng; Chow, Sy-Miin; Ibrahim, Joseph G; Zhu, Hongtu
2017-12-01
Many psychological concepts are unobserved and usually represented as latent factors apprehended through multiple observed indicators. When multiple-subject multivariate time series data are available, dynamic factor analysis models with random effects offer one way of modeling patterns of within- and between-person variations by combining factor analysis and time series analysis at the factor level. Using the Dirichlet process (DP) as a nonparametric prior for individual-specific time series parameters further allows the distributional forms of these parameters to deviate from commonly imposed (e.g., normal or other symmetric) functional forms, arising as a result of these parameters' restricted ranges. Given the complexity of such models, a thorough sensitivity analysis is critical but computationally prohibitive. We propose a Bayesian local influence method that allows for simultaneous sensitivity analysis of multiple modeling components within a single fitting of the model of choice. Five illustrations and an empirical example are provided to demonstrate the utility of the proposed approach in facilitating the detection of outlying cases and common sources of misspecification in dynamic factor analysis models, as well as identification of modeling components that are sensitive to changes in the DP prior specification.
Directory of Open Access Journals (Sweden)
Tan Zhou
2017-12-01
Full Text Available A plethora of information contained in full-waveform (FW Light Detection and Ranging (LiDAR data offers prospects for characterizing vegetation structures. This study aims to investigate the capacity of FW LiDAR data alone for tree species identification through the integration of waveform metrics with machine learning methods and Bayesian inference. Specifically, we first conducted automatic tree segmentation based on the waveform-based canopy height model (CHM using three approaches including TreeVaW, watershed algorithms and the combination of TreeVaW and watershed (TW algorithms. Subsequently, the Random forests (RF and Conditional inference forests (CF models were employed to identify important tree-level waveform metrics derived from three distinct sources, such as raw waveforms, composite waveforms, the waveform-based point cloud and the combined variables from these three sources. Further, we discriminated tree (gray pine, blue oak, interior live oak and shrub species through the RF, CF and Bayesian multinomial logistic regression (BMLR using important waveform metrics identified in this study. Results of the tree segmentation demonstrated that the TW algorithms outperformed other algorithms for delineating individual tree crowns. The CF model overcomes waveform metrics selection bias caused by the RF model which favors correlated metrics and enhances the accuracy of subsequent classification. We also found that composite waveforms are more informative than raw waveforms and waveform-based point cloud for characterizing tree species in our study area. Both classical machine learning methods (the RF and CF and the BMLR generated satisfactory average overall accuracy (74% for the RF, 77% for the CF and 81% for the BMLR and the BMLR slightly outperformed the other two methods. However, these three methods suffered from low individual classification accuracy for the blue oak which is prone to being misclassified as the interior live oak due
Chen, Duxin; Xu, Bowen; Zhu, Tao; Zhou, Tao; Zhang, Hai-Tao
2017-08-01
Coordination shall be deemed to the result of interindividual interaction among natural gregarious animal groups. However, revealing the underlying interaction rules and decision-making strategies governing highly coordinated motion in bird flocks is still a long-standing challenge. Based on analysis of high spatial-temporal resolution GPS data of three pigeon flocks, we extract the hidden interaction principle by using a newly emerging machine learning method, namely the sparse Bayesian learning. It is observed that the interaction probability has an inflection point at pairwise distance of 3-4 m closer than the average maximum interindividual distance, after which it decays strictly with rising pairwise metric distances. Significantly, the density of spatial neighbor distribution is strongly anisotropic, with an evident lack of interactions along individual velocity. Thus, it is found that in small-sized bird flocks, individuals reciprocally cooperate with a variational number of neighbors in metric space and tend to interact with closer time-varying neighbors, rather than interacting with a fixed number of topological ones. Finally, extensive numerical investigation is conducted to verify both the revealed interaction and decision-making principle during circular flights of pigeon flocks.
Ayaburi, Emmanuel Wusuhon Yanibo
2017-01-01
This dissertation investigates the effect of observational learning in crowdsourcing markets as a lens to identify appropriate mechanism(s) for sustaining this increasingly popular business model. Observational learning occurs when crowdsourcing participating agents obtain knowledge from signals they observe in the marketplace and incorporate such…
Bayesian Methods for the Physical Sciences. Learning from Examples in Astronomy and Physics.
Andreon, Stefano; Weaver, Brian
2015-05-01
Chapter 1: This chapter presents some basic steps for performing a good statistical analysis, all summarized in about one page. Chapter 2: This short chapter introduces the basics of probability theory inan intuitive fashion using simple examples. It also illustrates, again with examples, how to propagate errors and the difference between marginal and profile likelihoods. Chapter 3: This chapter introduces the computational tools and methods that we use for sampling from the posterior distribution. Since all numerical computations, and Bayesian ones are no exception, may end in errors, we also provide a few tips to check that the numerical computation is sampling from the posterior distribution. Chapter 4: Many of the concepts of building, running, and summarizing the resultsof a Bayesian analysis are described with this step-by-step guide using a basic (Gaussian) model. The chapter also introduces examples using Poisson and Binomial likelihoods, and how to combine repeated independent measurements. Chapter 5: All statistical analyses make assumptions, and Bayesian analyses are no exception. This chapter emphasizes that results depend on data and priors (assumptions). We illustrate this concept with examples where the prior plays greatly different roles, from major to negligible. We also provide some advice on how to look for information useful for sculpting the prior. Chapter 6: In this chapter we consider examples for which we want to estimate more than a single parameter. These common problems include estimating location and spread. We also consider examples that require the modeling of two populations (one we are interested in and a nuisance population) or averaging incompatible measurements. We also introduce quite complex examples dealing with upper limits and with a larger-than-expected scatter. Chapter 7: Rarely is a sample randomly selected from the population we wish to study. Often, samples are affected by selection effects, e.g., easier
Stochastic Online Learning in Dynamic Networks under Unknown Models
2016-08-02
The key is to develop online learning strategies at each individual node. Specifically, through local information exchange with its neighbors, each...infinitely repeated game with incomplete information and developed a dynamic pricing strategy referred to as Competitive and Cooperative Demand Learning...Stochastic Online Learning in Dynamic Networks under Unknown Models This research aims to develop fundamental theories and practical algorithms for
Beyond Problem-Based Learning: Using Dynamic PBL in Chemistry
Overton, Tina L.; Randles, Christopher A.
2015-01-01
This paper describes the development and implementation of a novel pedagogy, dynamic problem-based learning. The pedagogy utilises real-world problems that evolve throughout the problem-based learning activity and provide students with choice and different data sets. This new dynamic problem-based learning approach was utilised to teach…
Wu, Zhen; Liu, Yong; Liang, Zhongyao; Wu, Sifeng; Guo, Huaicheng
2017-06-01
Lake eutrophication is associated with excessive anthropogenic nutrients (mainly nitrogen (N) and phosphorus (P)) and unobserved internal nutrient cycling. Despite the advances in understanding the role of external loadings, the contribution of internal nutrient cycling is still an open question. A dynamic mass-balance model was developed to simulate and measure the contributions of internal cycling and external loading. It was based on the temporal Bayesian Hierarchical Framework (BHM), where we explored the seasonal patterns in the dynamics of nutrient cycling processes and the limitation of N and P on phytoplankton growth in hyper-eutrophic Lake Dianchi, China. The dynamic patterns of the five state variables (Chla, TP, ammonia, nitrate and organic N) were simulated based on the model. Five parameters (algae growth rate, sediment exchange rate of N and P, nitrification rate and denitrification rate) were estimated based on BHM. The model provided a good fit to observations. Our model results highlighted the role of internal cycling of N and P in Lake Dianchi. The internal cycling processes contributed more than external loading to the N and P changes in the water column. Further insights into the nutrient limitation analysis indicated that the sediment exchange of P determined the P limitation. Allowing for the contribution of denitrification to N removal, N was the more limiting nutrient in most of the time, however, P was the more important nutrient for eutrophication management. For Lake Dianchi, it would not be possible to recover solely by reducing the external watershed nutrient load; the mechanisms of internal cycling should also be considered as an approach to inhibit the release of sediments and to enhance denitrification. Copyright © 2017 Elsevier Ltd. All rights reserved.
Multidimensional (OLAP) Analysis for Designing Dynamic Learning Strategy
Rozeva, A.; Deliyska, B.
2010-10-01
Learning strategy in an intelligent learning system is generally elaborated on the basis of assessment of the following factors: learner's time for reaction, content of the learning object, amount of learning material in a learning object, learning object specification, e-learning medium and performance control. Current work proposes architecture for dynamic learning strategy design by implementing multidimensional analysis model of learning factors. The analysis model concerns on-line analytical processing (OLAP) of learner's data structured as multidimensional cube. Main components of the architecture are analysis agent for performing the OLAP operations on learner data cube, adaptation generator and knowledge selection agent for performing adaptive navigation in the learning object repository. The output of the analysis agent is involved in dynamic elaboration of learning strategy that fits best to learners profile and behavior. As a result an adaptive learning path for individual learner and for learner groups is generated.
Nonparametric bayesian reward segmentation for skill discovery using inverse reinforcement learning
CSIR Research Space (South Africa)
Ranchod, P
2015-10-01
Full Text Available We present a method for segmenting a set of unstructured demonstration trajectories to discover reusable skills using inverse reinforcement learning (IRL). Each skill is characterised by a latent reward function which the demonstrator is assumed...
Bayesian learning for spatial filtering in an EEG-based brain-computer interface.
Zhang, Haihong; Yang, Huijuan; Guan, Cuntai
2013-07-01
Spatial filtering for EEG feature extraction and classification is an important tool in brain-computer interface. However, there is generally no established theory that links spatial filtering directly to Bayes classification error. To address this issue, this paper proposes and studies a Bayesian analysis theory for spatial filtering in relation to Bayes error. Following the maximum entropy principle, we introduce a gamma probability model for describing single-trial EEG power features. We then formulate and analyze the theoretical relationship between Bayes classification error and the so-called Rayleigh quotient, which is a function of spatial filters and basically measures the ratio in power features between two classes. This paper also reports our extensive study that examines the theory and its use in classification, using three publicly available EEG data sets and state-of-the-art spatial filtering techniques and various classifiers. Specifically, we validate the positive relationship between Bayes error and Rayleigh quotient in real EEG power features. Finally, we demonstrate that the Bayes error can be practically reduced by applying a new spatial filter with lower Rayleigh quotient.
Hernandez Lahme, Damian; Sober, Samuel; Nemenman, Ilya
Important questions in computational neuroscience are whether, how much, and how information is encoded in the precise timing of neural action potentials. We recently demonstrated that, in the premotor cortex during vocal control in songbirds, spike timing is far more informative about upcoming behavior than is spike rate (Tang et al, 2014). However, identification of complete dictionaries that relate spike timing patterns with the controled behavior remains an elusive problem. Here we present a computational approach to deciphering such codes for individual neurons in the songbird premotor area RA, an analog of mammalian primary motor cortex. Specifically, we analyze which multispike patterns of neural activity predict features of the upcoming vocalization, and hence are important codewords. We use a recently introduced Bayesian Ising Approximation, which properly accounts for the fact that many codewords overlap and hence are not independent. Our results show which complex, temporally precise multispike combinations are used by individual neurons to control acoustic features of the produced song, and that these code words are different across individual neurons and across different acoustic features. This work was supported, in part, by JSMF Grant 220020321, NSF Grant 1208126, NIH Grant NS084844 and NIH Grant 1 R01 EB022872.
Soufan, Othman
2016-01-01
Abstract Background Mining high-throughput screening (HTS) assays is key for enhancing decisions in the area of drug repositioning and drug discovery. However, many challenges are encountered in the process of developing suitable and accurate methods for extracting useful information from these assays. Virtual screening and a wide variety of databases, methods and solutions proposed to-date, did not completely overcome these challenges. This study is based on a multi-label classification (MLC) technique for modeling correlations between several HTS assays, meaning that a single prediction represents a subset of assigned correlated labels instead of one label. Thus, the devised method provides an increased probability for more accurate predictions of compounds that were not tested in particular assays. Results Here we present DRABAL, a novel MLC solution that incorporates structure learning of a Bayesian network as a step to model dependency between the HTS assays. In this study, DRABAL was used to process more than 1.4 million interactions of over 400,000 compounds and analyze the existing relationships between five large HTS assays from the PubChem BioAssay Database. Compared to different MLC methods, DRABAL significantly improves the F1Score by about 22%, on average. We further illustrated usefulness and utility of DRABAL through screening FDA approved drugs and reported ones that have a high probability to interact with several targets, thus enabling drug-multi-target repositioning. Specifically DRABAL suggests the Thiabendazole drug as a common activator of the NCP1 and Rab-9A proteins, both of which are designed to identify treatment modalities for the Niemannâ Pick type C disease. Conclusion We developed a novel MLC solution based on a Bayesian active learning framework to overcome the challenge of lacking fully labeled training data and exploit actual dependencies between the HTS assays. The solution is motivated by the need to model dependencies between
Anacleto, Osvaldo; Queen, Catriona; Albers, Casper J.
Traffic flow data are routinely collected for many networks worldwide. These invariably large data sets can be used as part of a traffic management system, for which good traffic flow forecasting models are crucial. The linear multiregression dynamic model (LMDM) has been shown to be promising for
Xue, Jie; Gui, Dongwei; Lei, Jiaqiang; Sun, Huaiwei; Zeng, Fanjiang; Feng, Xinlong
2017-12-01
Agriculture and the eco-environment are increasingly competing for water. The extension of intensive farmland for ensuring food security has resulted in excessive water exploitation by agriculture. Consequently, this has led to a lack of water supply in natural ecosystems. This paper proposes a trade-off framework to coordinate the water-use conflict between agriculture and the eco-environment, based on economic compensation for irrigation stakeholders. A hybrid Bayesian network (HBN) is developed to implement the framework, including: (a) agricultural water shortage assessments after meeting environmental flows; (b) water-use tradeoff analysis between agricultural irrigation and environmental flows using the HBN; and (c) quantification of the agricultural economic compensation for different irrigation stakeholders. The constructed HBN is computed by dynamic discretization, which is a more robust and accurate propagation algorithm than general static discretization. A case study of the Qira oasis area in Northwest China demonstrates that the water trade-off based on economic compensation depends on the available water supply and environmental flows at different levels. Agricultural irrigation water extracted for grain crops should be preferentially guaranteed to ensure food security, in spite of higher economic compensation in other cash crops' irrigation for water coordination. Updating water-saving engineering and adopting drip irrigation technology in agricultural facilities after satisfying environmental flows would greatly relieve agricultural water shortage and save the economic compensation for different irrigation stakeholders. The approach in this study can be easily applied in water-stressed areas worldwide for dealing with water competition.
Cognitive Strategies for Learning from Static and Dynamic Visuals.
Lewalter, D.
2003-01-01
Studied the effects of including static or dynamic visuals in an expository text on a learning outcome and the use of learning strategies when working with these visuals. Results for 60 undergraduates for both types of illustration indicate different frequencies in the use of learning strategies relevant for the learning outcome. (SLD)
Cognitive Models for Learning to Control Dynamic Systems
National Research Council Canada - National Science Library
Eberhart, Russ; Hu, Xiaohui; Chen, Yaobin
2008-01-01
Report developed under STTR contract for topic "Cognitive models for learning to control dynamic systems" demonstrated a swarm intelligence learning algorithm and its application in unmanned aerial vehicle (UAV) mission planning...
Korattikara, A.; Rathod, V.; Murphy, K.; Welling, M.; Cortes, C.; Lawrence, N.D.; Lee, D.D.; Sugiyama, M.; Garnett, R.
2015-01-01
We consider the problem of Bayesian parameter estimation for deep neural networks, which is important in problem settings where we may have little data, and/ or where we need accurate posterior predictive densities p(y|x, D), e.g., for applications involving bandits or active learning. One simple
Frank M. Bass; Norris Bruce; Sumit Majumdar; B. P. S. Murthi
2007-01-01
Models of advertising response implicitly assume that the entire advertising budget is spent on disseminating one message. In practice, managers use different themes of advertising (for example, price advertisements versus product advertisements) and within each theme they employ different versions of an advertisement. In this study, we evaluate the dynamic effects of different themes of advertising that have been employed in a campaign. We develop a model that jointly considers the effects o...
Estimation of Input Function from Dynamic PET Brain Data Using Bayesian Blind Source Separation
Czech Academy of Sciences Publication Activity Database
Tichý, Ondřej; Šmídl, Václav
2015-01-01
Roč. 12, č. 4 (2015), s. 1273-1287 ISSN 1820-0214 R&D Projects: GA ČR GA13-29225S Institutional support: RVO:67985556 Keywords : blind source separation * Variational Bayes method * dynamic PET * input function * deconvolution Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 0.623, year: 2015 http://library.utia.cas.cz/separaty/2015/AS/tichy-0450509.pdf
Ma, Yingzhao; Hong, Yang; Chen, Yang; Yang, Yuan; Tang, Guoqiang; Yao, Yunjun; Long, Di; Li, Changmin; Han, Zhongying; Liu, Ronghua
2018-01-01
Accurate estimation of precipitation from satellites at high spatiotemporal scales over the Tibetan Plateau (TP) remains a challenge. In this study, we proposed a general framework for blending multiple satellite precipitation data using the dynamic Bayesian model averaging (BMA) algorithm. The blended experiment was performed at a daily 0.25° grid scale for 2007-2012 among Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA) 3B42RT and 3B42V7, Climate Prediction Center MORPHing technique (CMORPH), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR). First, the BMA weights were optimized using the expectation-maximization (EM) method for each member on each day at 200 calibrated sites and then interpolated to the entire plateau using the ordinary kriging (OK) approach. Thus, the merging data were produced by weighted sums of the individuals over the plateau. The dynamic BMA approach showed better performance with a smaller root-mean-square error (RMSE) of 6.77 mm/day, higher correlation coefficient of 0.592, and closer Euclid value of 0.833, compared to the individuals at 15 validated sites. Moreover, BMA has proven to be more robust in terms of seasonality, topography, and other parameters than traditional ensemble methods including simple model averaging (SMA) and one-outlier removed (OOR). Error analysis between BMA and the state-of-the-art IMERG in the summer of 2014 further proved that the performance of BMA was superior with respect to multisatellite precipitation data merging. This study demonstrates that BMA provides a new solution for blending multiple satellite data in regions with limited gauges.
Zhang, Zhilin; Jung, Tzyy-Ping; Makeig, Scott; Rao, Bhaskar D
2013-02-01
Fetal ECG (FECG) telemonitoring is an important branch in telemedicine. The design of a telemonitoring system via a wireless body area network with low energy consumption for ambulatory use is highly desirable. As an emerging technique, compressed sensing (CS) shows great promise in compressing/reconstructing data with low energy consumption. However, due to some specific characteristics of raw FECG recordings such as nonsparsity and strong noise contamination, current CS algorithms generally fail in this application. This paper proposes to use the block sparse Bayesian learning framework to compress/reconstruct nonsparse raw FECG recordings. Experimental results show that the framework can reconstruct the raw recordings with high quality. Especially, the reconstruction does not destroy the interdependence relation among the multichannel recordings. This ensures that the independent component analysis decomposition of the reconstructed recordings has high fidelity. Furthermore, the framework allows the use of a sparse binary sensing matrix with much fewer nonzero entries to compress recordings. Particularly, each column of the matrix can contain only two nonzero entries. This shows that the framework, compared to other algorithms such as current CS algorithms and wavelet algorithms, can greatly reduce code execution in CPU in the data compression stage.
Bayesian structure learning for Markov Random Fields with a spike and slab prior
Chen, Y.; Welling, M.; de Freitas, N.; Murphy, K.
2012-01-01
In recent years a number of methods have been developed for automatically learning the (sparse) connectivity structure of Markov Random Fields. These methods are mostly based on L1-regularized optimization which has a number of disadvantages such as the inability to assess model uncertainty and
Shaping the learning curve: epigenetic dynamics in neural plasticity
Directory of Open Access Journals (Sweden)
Zohar Ziv Bronfman
2014-07-01
Full Text Available A key characteristic of learning and neural plasticity is state-dependent acquisition dynamics reflected by the non-linear learning curve that links increase in learning with practice. Here we propose that the manner by which epigenetic states of individual cells change during learning contributes to the shape of the neural and behavioral learning curve. We base our suggestion on recent studies showing that epigenetic mechanisms such as DNA methylation, histone acetylation and RNA-mediated gene regulation are intimately involved in the establishment and maintenance of long-term neural plasticity, reflecting specific learning-histories and influencing future learning. Our model, which is the first to suggest a dynamic molecular account of the shape of the learning curve, leads to several testable predictions regarding the link between epigenetic dynamics at the promoter, gene-network and neural-network levels. This perspective opens up new avenues for therapeutic interventions in neurological pathologies.
Lesaffre, Emmanuel
2012-01-01
The growth of biostatistics has been phenomenal in recent years and has been marked by considerable technical innovation in both methodology and computational practicality. One area that has experienced significant growth is Bayesian methods. The growing use of Bayesian methodology has taken place partly due to an increasing number of practitioners valuing the Bayesian paradigm as matching that of scientific discovery. In addition, computational advances have allowed for more complex models to be fitted routinely to realistic data sets. Through examples, exercises and a combination of introd
Directory of Open Access Journals (Sweden)
Wang Shu-Qiang
2012-07-01
Full Text Available Abstract Background A key challenge in the post genome era is to identify genome-wide transcriptional regulatory networks, which specify the interactions between transcription factors and their target genes. Numerous methods have been developed for reconstructing gene regulatory networks from expression data. However, most of them are based on coarse grained qualitative models, and cannot provide a quantitative view of regulatory systems. Results A binding affinity based regulatory model is proposed to quantify the transcriptional regulatory network. Multiple quantities, including binding affinity and the activity level of transcription factor (TF are incorporated into a general learning model. The sequence features of the promoter and the possible occupancy of nucleosomes are exploited to estimate the binding probability of regulators. Comparing with the previous models that only employ microarray data, the proposed model can bridge the gap between the relative background frequency of the observed nucleotide and the gene's transcription rate. Conclusions We testify the proposed approach on two real-world microarray datasets. Experimental results show that the proposed model can effectively identify the parameters and the activity level of TF. Moreover, the kinetic parameters introduced in the proposed model can reveal more biological sense than previous models can do.
Qi, Wei; Liu, Junguo; Yang, Hong; Sweetapple, Chris
2018-03-01
Global precipitation products are very important datasets in flow simulations, especially in poorly gauged regions. Uncertainties resulting from precipitation products, hydrological models and their combinations vary with time and data magnitude, and undermine their application to flow simulations. However, previous studies have not quantified these uncertainties individually and explicitly. This study developed an ensemble-based dynamic Bayesian averaging approach (e-Bay) for deterministic discharge simulations using multiple global precipitation products and hydrological models. In this approach, the joint probability of precipitation products and hydrological models being correct is quantified based on uncertainties in maximum and mean estimation, posterior probability is quantified as functions of the magnitude and timing of discharges, and the law of total probability is implemented to calculate expected discharges. Six global fine-resolution precipitation products and two hydrological models of different complexities are included in an illustrative application. e-Bay can effectively quantify uncertainties and therefore generate better deterministic discharges than traditional approaches (weighted average methods with equal and varying weights and maximum likelihood approach). The mean Nash-Sutcliffe Efficiency values of e-Bay are up to 0.97 and 0.85 in training and validation periods respectively, which are at least 0.06 and 0.13 higher than traditional approaches. In addition, with increased training data, assessment criteria values of e-Bay show smaller fluctuations than traditional approaches and its performance becomes outstanding. The proposed e-Bay approach bridges the gap between global precipitation products and their pragmatic applications to discharge simulations, and is beneficial to water resources management in ungauged or poorly gauged regions across the world.
Directory of Open Access Journals (Sweden)
Mario A Pardo
Full Text Available We inferred the population densities of blue whales (Balaenoptera musculus and short-beaked common dolphins (Delphinus delphis in the Northeast Pacific Ocean as functions of the water-column's physical structure by implementing hierarchical models in a Bayesian framework. This approach allowed us to propagate the uncertainty of the field observations into the inference of species-habitat relationships and to generate spatially explicit population density predictions with reduced effects of sampling heterogeneity. Our hypothesis was that the large-scale spatial distributions of these two cetacean species respond primarily to ecological processes resulting from shoaling and outcropping of the pycnocline in regions of wind-forced upwelling and eddy-like circulation. Physically, these processes affect the thermodynamic balance of the water column, decreasing its volume and thus the height of the absolute dynamic topography (ADT. Biologically, they lead to elevated primary productivity and persistent aggregation of low-trophic-level prey. Unlike other remotely sensed variables, ADT provides information about the structure of the entire water column and it is also routinely measured at high spatial-temporal resolution by satellite altimeters with uniform global coverage. Our models provide spatially explicit population density predictions for both species, even in areas where the pycnocline shoals but does not outcrop (e.g. the Costa Rica Dome and the North Equatorial Countercurrent thermocline ridge. Interannual variations in distribution during El Niño anomalies suggest that the population density of both species decreases dramatically in the Equatorial Cold Tongue and the Costa Rica Dome, and that their distributions retract to particular areas that remain productive, such as the more oceanic waters in the central California Current System, the northern Gulf of California, the North Equatorial Countercurrent thermocline ridge, and the more
ZHOU, Lin
1996-01-01
In this paper I consider social choices under uncertainty. I prove that any social choice rule that satisfies independence of irrelevant alternatives, translation invariance, and weak anonymity is consistent with ex post Bayesian utilitarianism
Dynamic Influence of Emotional States on Novel Word Learning
Guo, Jingjing; Zou, Tiantian; Peng, Danling
2018-01-01
Many researchers realize that it's unrealistic to isolate language learning and processing from emotions. However, few studies on language learning have taken emotions into consideration so far, so that the probable influences of emotions on language learning are unclear. The current study thereby aimed to examine the effects of emotional states on novel word learning and their dynamic changes with learning continuing and task varying. Positive, negative or neutral pictures were employed to induce a given emotional state, and then participants learned the novel words through association with line-drawing pictures in four successive learning phases. At the end of each learning phase, participants were instructed to fulfill a semantic category judgment task (in Experiment 1) or a word-picture semantic consistency judgment task (in Experiment 2) to explore the effects of emotional states on different depths of word learning. Converging results demonstrated that negative emotional state led to worse performance compared with neutral condition; however, how positive emotional state affected learning varied with learning task. Specifically, a facilitative role of positive emotional state in semantic category learning was observed but disappeared in word specific meaning learning. Moreover, the emotional modulation on novel word learning was quite dynamic and changeable with learning continuing, and the final attainment of the learned words tended to be similar under different emotional states. The findings suggest that the impact of emotion can be offset when novel words became more and more familiar and a part of existent lexicon. PMID:29695994
Using consensus bayesian network to model the reactive oxygen species regulatory pathway.
Directory of Open Access Journals (Sweden)
Liangdong Hu
Full Text Available Bayesian network is one of the most successful graph models for representing the reactive oxygen species regulatory pathway. With the increasing number of microarray measurements, it is possible to construct the bayesian network from microarray data directly. Although large numbers of bayesian network learning algorithms have been developed, when applying them to learn bayesian networks from microarray data, the accuracies are low due to that the databases they used to learn bayesian networks contain too few microarray data. In this paper, we propose a consensus bayesian network which is constructed by combining bayesian networks from relevant literatures and bayesian networks learned from microarray data. It would have a higher accuracy than the bayesian networks learned from one database. In the experiment, we validated the bayesian network combination algorithm on several classic machine learning databases and used the consensus bayesian network to model the Escherichia coli's ROS pathway.
Structure Learning in Stochastic Non-linear Dynamical Systems
Morris, R. D.; Smelyanskiy, V. N.; Luchinsky, D. G.
2005-12-01
A great many systems can be modeled in the non-linear dynamical systems framework, as x˙ = f(x) + ξ(t), where f(x) is the potential function for the system, and ξ(t) is the driving noise. Modeling the potential using a set of basis functions, we derive the posterior for the basis coefficients. A more challenging problem is to determine the set of basis functions that are required to model a particular system. We show that using the Bayesian Information Criteria (BIC) to rank models, and the beam search technique, that we can accurately determine the structure of simple non-linear dynamical system models, and the structure of the coupling between non-linear dynamical systems where the individual systems are known. This last case has important ecological applications, for example in predator-prey systems, where the very structure of the coupling between predator-prey pairs can have great ecological significance.
Jensen, Dan B; Hogeveen, Henk; De Vries, Albert
2016-09-01
Rapid detection of dairy cow mastitis is important so corrective action can be taken as soon as possible. Automatically collected sensor data used to monitor the performance and the health state of the cow could be useful for rapid detection of mastitis while reducing the labor needs for monitoring. The state of the art in combining sensor data to predict clinical mastitis still does not perform well enough to be applied in practice. Our objective was to combine a multivariate dynamic linear model (DLM) with a naïve Bayesian classifier (NBC) in a novel method using sensor and nonsensor data to detect clinical cases of mastitis. We also evaluated reductions in the number of sensors for detecting mastitis. With the DLM, we co-modeled 7 sources of sensor data (milk yield, fat, protein, lactose, conductivity, blood, body weight) collected at each milking for individual cows to produce one-step-ahead forecasts for each sensor. The observations were subsequently categorized according to the errors of the forecasted values and the estimated forecast variance. The categorized sensor data were combined with other data pertaining to the cow (week in milk, parity, mastitis history, somatic cell count category, and season) using Bayes' theorem, which produced a combined probability of the cow having clinical mastitis. If this probability was above a set threshold, the cow was classified as mastitis positive. To illustrate the performance of our method, we used sensor data from 1,003,207 milkings from the University of Florida Dairy Unit collected from 2008 to 2014. Of these, 2,907 milkings were associated with recorded cases of clinical mastitis. Using the DLM/NBC method, we reached an area under the receiver operating characteristic curve of 0.89, with a specificity of 0.81 when the sensitivity was set at 0.80. Specificities with omissions of sensor data ranged from 0.58 to 0.81. These results are comparable to other studies, but differences in data quality, definitions of
Jameel, M. Y.; Brewer, S.; Fiorella, R.; Tipple, B. J.; Bowen, G. J.; Terry, S.
2017-12-01
Public water supply systems (PWSS) are complex distribution systems and critical infrastructure, making them vulnerable to physical disruption and contamination. Exploring the susceptibility of PWSS to such perturbations requires detailed knowledge of the supply system structure and operation. Although the physical structure of supply systems (i.e., pipeline connection) is usually well documented for developed cities, the actual flow patterns of water in these systems are typically unknown or estimated based on hydrodynamic models with limited observational validation. Here, we present a novel method for mapping the flow structure of water in a large, complex PWSS, building upon recent work highlighting the potential of stable isotopes of water (SIW) to document water management practices within complex PWSS. We sampled a major water distribution system of the Salt Lake Valley, Utah, measuring SIW of water sources, treatment facilities, and numerous sites within in the supply system. We then developed a hierarchical Bayesian (HB) isotope mixing model to quantify the proportion of water supplied by different sources at sites within the supply system. Known production volumes and spatial distance effects were used to define the prior probabilities for each source; however, we did not include other physical information about the supply system. Our results were in general agreement with those obtained by hydrodynamic models and provide quantitative estimates of contributions of different water sources to a given site along with robust estimates of uncertainty. Secondary properties of the supply system, such as regions of "static" and "dynamic" source (e.g., regions supplied dominantly by one source vs. those experiencing active mixing between multiple sources), can be inferred from the results. The isotope-based HB isotope mixing model offers a new investigative technique for analyzing PWSS and documenting aspects of supply system structure and operation that are
DEFF Research Database (Denmark)
Liu, Dedi; Li, Xiang; Guo, Shenglian
2015-01-01
Dynamic control of the flood limiting water level (FLWL) is a valuable and effective way to maximize the benefits from reservoir operation without exceeding the design risk. In order to analyze the impacts of input uncertainty, a Bayesian forecasting system (BFS) is adopted. Applying quantile water...... inflow values and their uncertainties obtained from the BFS, the reservoir operation results from different schemes can be analyzed in terms of benefits, dam safety, and downstream impacts during the flood season. When the reservoir FLWL dynamic control operation is implemented, there are two fundamental......, also deterministic water inflow was tested. The proposed model in the paper emphasizes the importance of analyzing the uncertainties of the water inflow forecasting system for real-time dynamic control of the FLWL for reservoir operation. For the case study, the selected quantile inflow from...
R.W. Strachan (Rodney); H.K. van Dijk (Herman)
2008-01-01
textabstractA Bayesian model averaging procedure is presented that makes use of a finite mixture of many model structures within the class of vector autoregressive (VAR) processes. It is applied to two empirical issues. First, stability of the Great Ratios in U.S. macro-economic time series is
Rosmawati
2014-01-01
Dynamic systems theory (DST) is presented in this article as a suitable approach to research the acquisition of second language (L2) because of its close alignment with the process of second language learning. Through a process of identifying and comparing the characteristics of a dynamic system with the process of L2 learning, this article…
Autonomous learning by simple dynamical systems with delayed feedback.
Kaluza, Pablo; Mikhailov, Alexander S
2014-09-01
A general scheme for the construction of dynamical systems able to learn generation of the desired kinds of dynamics through adjustment of their internal structure is proposed. The scheme involves intrinsic time-delayed feedback to steer the dynamics towards the target performance. As an example, a system of coupled phase oscillators, which can, by changing the weights of connections between its elements, evolve to a dynamical state with the prescribed (low or high) synchronization level, is considered and investigated.
Machine learning concepts in coherent optical communication systems
DEFF Research Database (Denmark)
Zibar, Darko; Schäffer, Christian G.
2014-01-01
Powerful statistical signal processing methods, used by the machine learning community, are addressed and linked to current problems in coherent optical communication. Bayesian filtering methods are presented and applied for nonlinear dynamic state tracking. © 2014 OSA.......Powerful statistical signal processing methods, used by the machine learning community, are addressed and linked to current problems in coherent optical communication. Bayesian filtering methods are presented and applied for nonlinear dynamic state tracking. © 2014 OSA....
Simulation of noisy dynamical system by Deep Learning
Yeo, Kyongmin
2017-11-01
Deep learning has attracted huge attention due to its powerful representation capability. However, most of the studies on deep learning have been focused on visual analytics or language modeling and the capability of the deep learning in modeling dynamical systems is not well understood. In this study, we use a recurrent neural network to model noisy nonlinear dynamical systems. In particular, we use a long short-term memory (LSTM) network, which constructs internal nonlinear dynamics systems. We propose a cross-entropy loss with spatial ridge regularization to learn a non-stationary conditional probability distribution from a noisy nonlinear dynamical system. A Monte Carlo procedure to perform time-marching simulations by using the LSTM is presented. The behavior of the LSTM is studied by using noisy, forced Van der Pol oscillator and Ikeda equation.
Baur, Brittany; Bozdag, Serdar
2015-04-01
One of the challenging and important computational problems in systems biology is to infer gene regulatory networks (GRNs) of biological systems. Several methods that exploit gene expression data have been developed to tackle this problem. In this study, we propose the use of copy number and DNA methylation data to infer GRNs. We developed an algorithm that scores regulatory interactions between genes based on canonical correlation analysis. In this algorithm, copy number or DNA methylation variables are treated as potential regulator variables, and expression variables are treated as potential target variables. We first validated that the canonical correlation analysis method is able to infer true interactions in high accuracy. We showed that the use of DNA methylation or copy number datasets leads to improved inference over steady-state expression. Our results also showed that epigenetic and structural information could be used to infer directionality of regulatory interactions. Additional improvements in GRN inference can be gleaned from incorporating the result in an informative prior in a dynamic Bayesian algorithm. This is the first study that incorporates copy number and DNA methylation into an informative prior in dynamic Bayesian framework. By closely examining top-scoring interactions with different sources of epigenetic or structural information, we also identified potential novel regulatory interactions.
Effective Bayesian Transfer Learning
2010-03-01
the class of algorithms analyzed by Bartlett’s work under task R4). With emphasis on transferring one type of objects to another, (e.g., coffee cups...obstacles, so those are temporarily pruned from the graph. In addition, the start and goal locations may not be currently included in the graph. They carried...Transfer Level 3 Varying shape within class Task A: Instances of an object from the same class. ( Coffee mug) Task B: Instances of a different object
Institute of Scientific and Technical Information of China (English)
Concha Bielza; Juan A.Fernández del Pozo; Pedro Larra(n)aga
2013-01-01
Parameter setting for evolutionary algorithms is still an important issue in evolutionary computation.There are two main approaches to parameter setting:parameter tuning and parameter control.In this paper,we introduce self-adaptive parameter control of a genetic algorithm based on Bayesian network learning and simulation.The nodes of this Bayesian network are genetic algorithm parameters to be controlled.Its structure captures probabilistic conditional (in)dependence relationships between the parameters.They are learned from the best individuals,i.e.,the best configurations of the genetic algorithm.Individuals are evaluated by running the genetic algorithm for the respective parameter configuration.Since all these runs are time-consuming tasks,each genetic algorithm uses a small-sized population and is stopped before convergence.In this way promising individuals should not be lost.Experiments with an optimal search problem for simultaneous row and column orderings yield the same optima as state-of-the-art methods but with a sharp reduction in computational time.Moreover,our approach can cope with as yet unsolved high-dimensional problems.
Integrating Dynamic Mathematics Software into Cooperative Learning Environments in Mathematics
Zengin, Yilmaz; Tatar, Enver
2017-01-01
The aim of this study was to evaluate the implementation of the cooperative learning model supported with dynamic mathematics software (DMS), that is a reflection of constructivist learning theory in the classroom environment, in the teaching of mathematics. For this purpose, a workshop was conducted with the volunteer teachers on the…
Bayesian Recurrent Neural Network for Language Modeling.
Chien, Jen-Tzung; Ku, Yuan-Chu
2016-02-01
A language model (LM) is calculated as the probability of a word sequence that provides the solution to word prediction for a variety of information systems. A recurrent neural network (RNN) is powerful to learn the large-span dynamics of a word sequence in the continuous space. However, the training of the RNN-LM is an ill-posed problem because of too many parameters from a large dictionary size and a high-dimensional hidden layer. This paper presents a Bayesian approach to regularize the RNN-LM and apply it for continuous speech recognition. We aim to penalize the too complicated RNN-LM by compensating for the uncertainty of the estimated model parameters, which is represented by a Gaussian prior. The objective function in a Bayesian classification network is formed as the regularized cross-entropy error function. The regularized model is constructed not only by calculating the regularized parameters according to the maximum a posteriori criterion but also by estimating the Gaussian hyperparameter by maximizing the marginal likelihood. A rapid approximation to a Hessian matrix is developed to implement the Bayesian RNN-LM (BRNN-LM) by selecting a small set of salient outer-products. The proposed BRNN-LM achieves a sparser model than the RNN-LM. Experiments on different corpora show the robustness of system performance by applying the rapid BRNN-LM under different conditions.
Bayesian ARTMAP for regression.
Sasu, L M; Andonie, R
2013-10-01
Bayesian ARTMAP (BA) is a recently introduced neural architecture which uses a combination of Fuzzy ARTMAP competitive learning and Bayesian learning. Training is generally performed online, in a single-epoch. During training, BA creates input data clusters as Gaussian categories, and also infers the conditional probabilities between input patterns and categories, and between categories and classes. During prediction, BA uses Bayesian posterior probability estimation. So far, BA was used only for classification. The goal of this paper is to analyze the efficiency of BA for regression problems. Our contributions are: (i) we generalize the BA algorithm using the clustering functionality of both ART modules, and name it BA for Regression (BAR); (ii) we prove that BAR is a universal approximator with the best approximation property. In other words, BAR approximates arbitrarily well any continuous function (universal approximation) and, for every given continuous function, there is one in the set of BAR approximators situated at minimum distance (best approximation); (iii) we experimentally compare the online trained BAR with several neural models, on the following standard regression benchmarks: CPU Computer Hardware, Boston Housing, Wisconsin Breast Cancer, and Communities and Crime. Our results show that BAR is an appropriate tool for regression tasks, both for theoretical and practical reasons. Copyright © 2013 Elsevier Ltd. All rights reserved.
Multiagent Reinforcement Learning Dynamic Spectrum Access in Cognitive Radios
Directory of Open Access Journals (Sweden)
Wu Chun
2014-02-01
Full Text Available A multiuser independent Q-learning method which does not need information interaction is proposed for multiuser dynamic spectrum accessing in cognitive radios. The method adopts self-learning paradigm, in which each CR user performs reinforcement learning only through observing individual performance reward without spending communication resource on information interaction with others. The reward is defined suitably to present channel quality and channel conflict status. The learning strategy of sufficient exploration, preference for good channel, and punishment for channel conflict is designed to implement multiuser dynamic spectrum accessing. In two users two channels scenario, a fast learning algorithm is proposed and the convergence to maximal whole reward is proved. The simulation results show that, with the proposed method, the CR system can obtain convergence of Nash equilibrium with large probability and achieve great performance of whole reward.
Gradient descent learning algorithm overview: a general dynamical systems perspective.
Baldi, P
1995-01-01
Gives a unified treatment of gradient descent learning algorithms for neural networks using a general framework of dynamical systems. This general approach organizes and simplifies all the known algorithms and results which have been originally derived for different problems (fixed point/trajectory learning), for different models (discrete/continuous), for different architectures (forward/recurrent), and using different techniques (backpropagation, variational calculus, adjoint methods, etc.). The general approach can also be applied to derive new algorithms. The author then briefly examines some of the complexity issues and limitations intrinsic to gradient descent learning. Throughout the paper, the author focuses on the problem of trajectory learning.
A dynamic learning concept in early years’ education
DEFF Research Database (Denmark)
Broström, Stig
2017-01-01
-historical activity (play) theory, the author deduces four generally accepted play criteria that form the basis for the construction of a dynamic and play-based learning concept that has the three following cornerstones as focal points: (1) learning happens in activities where the child is an active participant...... and interacts and communicates with other people; (2) meaningful activities pave the way for children’s learning; these are activities where the child’s motive aligns with the goal of the activity; and (3) learning is seen as a productive and creative activity characterised by imagination....
International Nuclear Information System (INIS)
Wen Fang-Qing; Zhang Gong; Ben De
2015-01-01
This paper addresses the direction of arrival (DOA) estimation problem for the co-located multiple-input multiple-output (MIMO) radar with random arrays. The spatially distributed sparsity of the targets in the background makes compressive sensing (CS) desirable for DOA estimation. A spatial CS framework is presented, which links the DOA estimation problem to support recovery from a known over-complete dictionary. A modified statistical model is developed to accurately represent the intra-block correlation of the received signal. A structural sparsity Bayesian learning algorithm is proposed for the sparse recovery problem. The proposed algorithm, which exploits intra-signal correlation, is capable being applied to limited data support and low signal-to-noise ratio (SNR) scene. Furthermore, the proposed algorithm has less computation load compared to the classical Bayesian algorithm. Simulation results show that the proposed algorithm has a more accurate DOA estimation than the traditional multiple signal classification (MUSIC) algorithm and other CS recovery algorithms. (paper)
Wen, Fang-Qing; Zhang, Gong; Ben, De
2015-11-01
This paper addresses the direction of arrival (DOA) estimation problem for the co-located multiple-input multiple-output (MIMO) radar with random arrays. The spatially distributed sparsity of the targets in the background makes compressive sensing (CS) desirable for DOA estimation. A spatial CS framework is presented, which links the DOA estimation problem to support recovery from a known over-complete dictionary. A modified statistical model is developed to accurately represent the intra-block correlation of the received signal. A structural sparsity Bayesian learning algorithm is proposed for the sparse recovery problem. The proposed algorithm, which exploits intra-signal correlation, is capable being applied to limited data support and low signal-to-noise ratio (SNR) scene. Furthermore, the proposed algorithm has less computation load compared to the classical Bayesian algorithm. Simulation results show that the proposed algorithm has a more accurate DOA estimation than the traditional multiple signal classification (MUSIC) algorithm and other CS recovery algorithms. Project supported by the National Natural Science Foundation of China (Grant Nos. 61071163, 61271327, and 61471191), the Funding for Outstanding Doctoral Dissertation in Nanjing University of Aeronautics and Astronautics, China (Grant No. BCXJ14-08), the Funding of Innovation Program for Graduate Education of Jiangsu Province, China (Grant No. KYLX 0277), the Fundamental Research Funds for the Central Universities, China (Grant No. 3082015NP2015504), and the Priority Academic Program Development of Jiangsu Higher Education Institutions (PADA), China.
Norros, Veera; Laine, Marko; Lignell, Risto; Thingstad, Frede
2017-10-01
Methods for extracting empirically and theoretically sound parameter values are urgently needed in aquatic ecosystem modelling to describe key flows and their variation in the system. Here, we compare three Bayesian formulations for mechanistic model parameterization that differ in their assumptions about the variation in parameter values between various datasets: 1) global analysis - no variation, 2) separate analysis - independent variation and 3) hierarchical analysis - variation arising from a shared distribution defined by hyperparameters. We tested these methods, using computer-generated and empirical data, coupled with simplified and reasonably realistic plankton food web models, respectively. While all methods were adequate, the simulated example demonstrated that a well-designed hierarchical analysis can result in the most accurate and precise parameter estimates and predictions, due to its ability to combine information across datasets. However, our results also highlighted sensitivity to hyperparameter prior distributions as an important caveat of hierarchical analysis. In the more complex empirical example, hierarchical analysis was able to combine precise identification of parameter values with reasonably good predictive performance, although the ranking of the methods was less straightforward. We conclude that hierarchical Bayesian analysis is a promising tool for identifying key ecosystem-functioning parameters and their variation from empirical datasets.
Directory of Open Access Journals (Sweden)
Zeinab eMortezapouraghdam
2016-01-01
Full Text Available We study the effect of long-term habituation signatures of auditory selective attention reflected in the instantaneous phase information of the auditory event-related potentials (ERPs at four distinct stimuli levels of 60dB SPL, 70dB SPL, 80dB SPL and 90dB SPL. The analysis is based on the single-trial level. The effect of habituation can be observed in terms of the changes (jitter in the instantaneous phase information of ERPs. In particular, the absence of habituation is correlated with a consistently high phase synchronization over ERP trials.We estimate the changes in phase concentration over trials using a Bayesian approach, in which the phase is modeled as being drawn from a von Mises distribution with a concentration parameter which varies smoothly over trials. The smoothness assumption reflects the fact that habituation is a gradual process.We differentiate between different stimuli based on the relative changes and absolute values of the estimated concentration parameter using the proposed Bayesian model.
Steering the dynamics within reduced space through quantum learning control
International Nuclear Information System (INIS)
Kim, Young Sik
2003-01-01
In quantum dynamics of many-body systems, to identify the Hamiltonian becomes more difficult very rapidly as the number of degrees of freedom increases. In order to simplify the dynamics and to deduce dynamically relevant Hamiltonian information, it is desirable to control the dynamics to lie within a reduced space. With a judicious choice for the cost functional, the closed loop optimal control experiments can be manipulated efficiently to steer the dynamics to lie within a subspace of the system eigenstates without requiring any prior detailed knowledge about the system Hamiltonian. The procedure is simulated for optimally controlled population transfer experiments in the system of two degrees of freedom. To show the feasibility of steering the dynamics to lie in a specified subspace, the learning algorithms guiding the dynamics are presented along with frequency filtering. The results demonstrate that the optimal control fields derive the system to the desired target state through the desired subspace
Threshold Learning Dynamics in Social Networks
González-Avella, Juan Carlos; Eguíluz, Victor M.; Marsili, Matteo; Vega-Redondo, Fernado; San Miguel, Maxi
2011-01-01
Social learning is defined as the ability of a population to aggregate information, a process which must crucially depend on the mechanisms of social interaction. Consumers choosing which product to buy, or voters deciding which option to take with respect to an important issue, typically confront external signals to the information gathered from their contacts. Economic models typically predict that correct social learning occurs in large populations unless some individuals display unbounded influence. We challenge this conclusion by showing that an intuitive threshold process of individual adjustment does not always lead to such social learning. We find, specifically, that three generic regimes exist separated by sharp discontinuous transitions. And only in one of them, where the threshold is within a suitable intermediate range, the population learns the correct information. In the other two, where the threshold is either too high or too low, the system either freezes or enters into persistent flux, respectively. These regimes are generally observed in different social networks (both complex or regular), but limited interaction is found to promote correct learning by enlarging the parameter region where it occurs. PMID:21637714
Sparse learning of stochastic dynamical equations
Boninsegna, Lorenzo; Nüske, Feliks; Clementi, Cecilia
2018-06-01
With the rapid increase of available data for complex systems, there is great interest in the extraction of physically relevant information from massive datasets. Recently, a framework called Sparse Identification of Nonlinear Dynamics (SINDy) has been introduced to identify the governing equations of dynamical systems from simulation data. In this study, we extend SINDy to stochastic dynamical systems which are frequently used to model biophysical processes. We prove the asymptotic correctness of stochastic SINDy in the infinite data limit, both in the original and projected variables. We discuss algorithms to solve the sparse regression problem arising from the practical implementation of SINDy and show that cross validation is an essential tool to determine the right level of sparsity. We demonstrate the proposed methodology on two test systems, namely, the diffusion in a one-dimensional potential and the projected dynamics of a two-dimensional diffusion process.
Self-learning Monte Carlo (dynamical biasing)
International Nuclear Information System (INIS)
Matthes, W.
1981-01-01
In many applications the histories of a normal Monte Carlo game rarely reach the target region. An approximate knowledge of the importance (with respect to the target) may be used to guide the particles more frequently into the target region. A Monte Carlo method is presented in which each history contributes to update the importance field such that eventually most target histories are sampled. It is a self-learning method in the sense that the procedure itself: (a) learns which histories are important (reach the target) and increases their probability; (b) reduces the probabilities of unimportant histories; (c) concentrates gradually on the more important target histories. (U.K.)
Becoming a Learning Organization Through Dynamic Business Process Management
Directory of Open Access Journals (Sweden)
Marek Szelągowski
2014-01-01
Full Text Available As customers demand easier access to individualized products and services, companies now face an ongoing problem of how to deliver flexible and innovative solutions while maintaining efficiency and competitiveness. In this environment, the only sustainable form of competitive advantage rests in the ability to learn faster than the competition (de Geus, 1988. The article returns to the somewhat forgotten concept of the learning organization and explores how its principles can be applied with the use of dynamic business process management (dynamic BPM. Enabling in this concept individual or team-based limited experimentation and providing conditions for learning though experience in the course of performing business processes allows for the constant creation of practical knowledge. This article provides examples of how dynamic BPM facilitates the constant creation and verification of practical knowledge, with the aim of improving and adapting processes to maintain the competitive advantage of the organization.
Bessiere, Pierre; Ahuactzin, Juan Manuel; Mekhnacha, Kamel
2013-01-01
Probability as an Alternative to Boolean LogicWhile logic is the mathematical foundation of rational reasoning and the fundamental principle of computing, it is restricted to problems where information is both complete and certain. However, many real-world problems, from financial investments to email filtering, are incomplete or uncertain in nature. Probability theory and Bayesian computing together provide an alternative framework to deal with incomplete and uncertain data. Decision-Making Tools and Methods for Incomplete and Uncertain DataEmphasizing probability as an alternative to Boolean
Video Game Learning Dynamics: Actionable Measures of Multidimensional Learning Trajectories
Reese, Debbie Denise; Tabachnick, Barbara G.; Kosko, Robert E.
2015-01-01
Valid, accessible, reusable methods for instructional video game design and embedded assessment can provide actionable information enhancing individual and collective achievement. Cyberlearning through game-based, metaphor-enhanced learning objects (CyGaMEs) design and embedded assessment quantify player behavior to study knowledge discovery and…
Dynamics of EEG functional connectivity during statistical learning.
Tóth, Brigitta; Janacsek, Karolina; Takács, Ádám; Kóbor, Andrea; Zavecz, Zsófia; Nemeth, Dezso
2017-10-01
Statistical learning is a fundamental mechanism of the brain, which extracts and represents regularities of our environment. Statistical learning is crucial in predictive processing, and in the acquisition of perceptual, motor, cognitive, and social skills. Although previous studies have revealed competitive neurocognitive processes underlying statistical learning, the neural communication of the related brain regions (functional connectivity, FC) has not yet been investigated. The present study aimed to fill this gap by investigating FC networks that promote statistical learning in humans. Young adults (N=28) performed a statistical learning task while 128-channels EEG was acquired. The task involved probabilistic sequences, which enabled to measure incidental/implicit learning of conditional probabilities. Phase synchronization in seven frequency bands was used to quantify FC between cortical regions during the first, second, and third periods of the learning task, respectively. Here we show that statistical learning is negatively correlated with FC of the anterior brain regions in slow (theta) and fast (beta) oscillations. These negative correlations increased as the learning progressed. Our findings provide evidence that dynamic antagonist brain networks serve a hallmark of statistical learning. Copyright © 2017 Elsevier Inc. All rights reserved.
Rapid learning dynamics in individual honeybees during classical conditioning
Directory of Open Access Journals (Sweden)
Evren ePamir
2014-09-01
Full Text Available Associative learning in insects has been studied extensively by a multitude of classical conditioning protocols. However, so far little emphasis has been put on the dynamics of learning in individuals. The honeybee is a well-established animal model for learning and memory. We here studied associative learning as expressed in individual behavior based on a large collection of data on olfactory classical conditioning (25 datasets, 3,298 animals. We show that the group-averaged learning curve and memory retention score confound three attributes of individual learning: the ability or inability to learn a given task, the generally fast acquisition of a conditioned response in learners, and the high stability of the conditioned response during consecutive training and memory retention trials. We reassessed the prevailing view that more training results in better memory performance and found that 24h memory retention can be indistinguishable after single-trial and multiple-trial conditioning in individuals. We explain how inter-individual differences in learning can be accommodated within the Rescorla-Wagner theory of associative learning. In both data-analysis and modeling we demonstrate how the conflict between population-level and single-animal perspectives on learning and memory can be disentangled.
Rapid learning dynamics in individual honeybees during classical conditioning.
Pamir, Evren; Szyszka, Paul; Scheiner, Ricarda; Nawrot, Martin P
2014-01-01
Associative learning in insects has been studied extensively by a multitude of classical conditioning protocols. However, so far little emphasis has been put on the dynamics of learning in individuals. The honeybee is a well-established animal model for learning and memory. We here studied associative learning as expressed in individual behavior based on a large collection of data on olfactory classical conditioning (25 datasets, 3298 animals). We show that the group-averaged learning curve and memory retention score confound three attributes of individual learning: the ability or inability to learn a given task, the generally fast acquisition of a conditioned response (CR) in learners, and the high stability of the CR during consecutive training and memory retention trials. We reassessed the prevailing view that more training results in better memory performance and found that 24 h memory retention can be indistinguishable after single-trial and multiple-trial conditioning in individuals. We explain how inter-individual differences in learning can be accommodated within the Rescorla-Wagner theory of associative learning. In both data-analysis and modeling we demonstrate how the conflict between population-level and single-animal perspectives on learning and memory can be disentangled.
Bayesian Analysis of Bubbles in Asset Prices
Directory of Open Access Journals (Sweden)
Andras Fulop
2017-10-01
Full Text Available We develop a new model where the dynamic structure of the asset price, after the fundamental value is removed, is subject to two different regimes. One regime reflects the normal period where the asset price divided by the dividend is assumed to follow a mean-reverting process around a stochastic long run mean. The second regime reflects the bubble period with explosive behavior. Stochastic switches between two regimes and non-constant probabilities of exit from the bubble regime are both allowed. A Bayesian learning approach is employed to jointly estimate the latent states and the model parameters in real time. An important feature of our Bayesian method is that we are able to deal with parameter uncertainty and at the same time, to learn about the states and the parameters sequentially, allowing for real time model analysis. This feature is particularly useful for market surveillance. Analysis using simulated data reveals that our method has good power properties for detecting bubbles. Empirical analysis using price-dividend ratios of S&P500 highlights the advantages of our method.
Dynamic pricing and learning with finite inventories
den Boer, A.V.; Zwart, Bert
2013-01-01
We study a dynamic pricing problem with finite inventory and parametric uncertainty on the demand distribution. Products are sold during selling seasons of finite length, and inventory that is unsold at the end of a selling season, perishes. The goal of the seller is to determine a pricing strategy
Dynamic pricing and learning with finite inventories
den Boer, A.V.; Zwart, Bert
We study a dynamic pricing problem with finite inventory and parametric uncertainty on the demand distribution. Products are sold during selling seasons of finite length, and inventory that is unsold at the end of a selling season perishes. The goal of the seller is to determine a pricing strategy
Dynamic Pricing and Learning with Finite Inventories
A.P. Zwart (Bert); A.V. den Boer (Arnoud)
2015-01-01
htmlabstractWe study a dynamic pricing problem with finite inventory and parametric uncertainty on the demand distribution. Products are sold during selling seasons of finite length, and inventory that is unsold at the end of a selling season perishes. The goal of the seller is to determine a
Dynamic pricing and learning with finite inventories
Boer, den A.V.; Zwart, B.
2015-01-01
We study a dynamic pricing problem with finite inventory and parametric uncertainty on the demand distribution. Products are sold during selling seasons of finite length, and inventory that is unsold at the end of a selling season perishes. The goal of the seller is to determine a pricing strategy
Learning automaton newtork and its dynamics. Gakushu automaton network to sono dynamics
Energy Technology Data Exchange (ETDEWEB)
Quan, F [Hiroshima-Denki Institute of Technology, Hiroshima (Jpaan); Unno, F; Hirata, H [Chiba Univ., Chiba (Japan)
1991-10-20
In order to construct a distributed processing system having learning automata as autonomous elements, a reinforcement learning network of the automaton is proposed and it{prime}s dynamics is investigated. In this paper, it is attempted to add another level of meaning to computational cooperativity by using a reinforcement learning network with generalized leaning automata. The collection of learning automata in the team situation acts as self-interested agents that work toward improving their performance with respect to their individual preference ordering. In the global state space of the network, the case of partially synchronous stochastic process is considered. In this case, the existence of mean field is shown and a reinforcement learning algorithm which can make the dynamics on the average reinforcement trajectory is presented. This algorithm is shown to have a high convergence speed as a result of a simple experiment. 14 refs., 9 figs.
Learning Methods for Dynamic Topic Modeling in Automated Behavior Analysis.
Isupova, Olga; Kuzin, Danil; Mihaylova, Lyudmila
2017-09-27
Semisupervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators' load. In the light of the necessity to process large volumes of video data and provide autonomous decisions, this paper proposes new learning algorithms for activity analysis in video. The activities and behaviors are described by a dynamic topic model. Two novel learning algorithms based on the expectation maximization approach and variational Bayes inference are proposed. Theoretical derivations of the posterior estimates of model parameters are given. The designed learning algorithms are compared with the Gibbs sampling inference scheme introduced earlier in the literature. A detailed comparison of the learning algorithms is presented on real video data. We also propose an anomaly localization procedure, elegantly embedded in the topic modeling framework. It is shown that the developed learning algorithms can achieve 95% success rate. The proposed framework can be applied to a number of areas, including transportation systems, security, and surveillance.
Deep Learning with Dynamic Computation Graphs
Looks, Moshe; Herreshoff, Marcello; Hutchins, DeLesley; Norvig, Peter
2017-01-01
Neural networks that compute over graph structures are a natural fit for problems in a variety of domains, including natural language (parse trees) and cheminformatics (molecular graphs). However, since the computation graph has a different shape and size for every input, such networks do not directly support batched training or inference. They are also difficult to implement in popular deep learning libraries, which are based on static data-flow graphs. We introduce a technique called dynami...
Learning to Estimate Dynamical State with Probabilistic Population Codes.
Directory of Open Access Journals (Sweden)
Joseph G Makin
2015-11-01
Full Text Available Tracking moving objects, including one's own body, is a fundamental ability of higher organisms, playing a central role in many perceptual and motor tasks. While it is unknown how the brain learns to follow and predict the dynamics of objects, it is known that this process of state estimation can be learned purely from the statistics of noisy observations. When the dynamics are simply linear with additive Gaussian noise, the optimal solution is the well known Kalman filter (KF, the parameters of which can be learned via latent-variable density estimation (the EM algorithm. The brain does not, however, directly manipulate matrices and vectors, but instead appears to represent probability distributions with the firing rates of population of neurons, "probabilistic population codes." We show that a recurrent neural network-a modified form of an exponential family harmonium (EFH-that takes a linear probabilistic population code as input can learn, without supervision, to estimate the state of a linear dynamical system. After observing a series of population responses (spike counts to the position of a moving object, the network learns to represent the velocity of the object and forms nearly optimal predictions about the position at the next time-step. This result builds on our previous work showing that a similar network can learn to perform multisensory integration and coordinate transformations for static stimuli. The receptive fields of the trained network also make qualitative predictions about the developing and learning brain: tuning gradually emerges for higher-order dynamical states not explicitly present in the inputs, appearing as delayed tuning for the lower-order states.
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
DEFF Research Database (Denmark)
Fraccaro, Marco; Kamronn, Simon Due; Paquet, Ulrich
2017-01-01
This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce the Kalman variational auto-encoder, a framework...... for unsupervised learning of sequential data that disentangles two latent representations: an object’s representation, coming from a recognition model, and a latent state describing its dynamics. As a result, the evolution of the world can be imagined and missing data imputed, both without the need to generate...
Dynamic Pricing and Learning with Finite Inventories
Zwart, Bert; Boer, Arnoud
2015-01-01
We study a dynamic pricing problem with finite inventory and parametric uncertainty on the demand distribution. Products are sold during selling seasons of finite length, and inventory that is unsold at the end of a selling season, perishes. The goal of the seller is to determine a pricing strategy that maximizes the expected revenue. Inference on the unknown parameters is made by maximum likelihood estimation. We propose a pricing strategy for this problem, and show that the Regret - which i...
Learning dynamics in research alliances: A panel data analysis
Duso, T.; Pennings, E.; Seldeslachts, J.
2010-01-01
The aim of this paper is to empirically test the determinants of Research Joint Ventures’ (RJVs) group dynamics. We develop a model based on learning and transaction cost theories, which represent the benefits and costs of RJV participation, respectively. According to our framework, firms at each
Learning and Understanding System Stability Using Illustrative Dynamic Texture Examples
Liu, Huaping; Xiao, Wei; Zhao, Hongyan; Sun, Fuchun
2014-01-01
System stability is a basic concept in courses on dynamic system analysis and control for undergraduate students with computer science backgrounds. Typically, this was taught using a simple simulation example of an inverted pendulum. Unfortunately, many difficult issues arise in the learning and understanding of the concepts of stability,…
Dynamic Textures Modeling via Joint Video Dictionary Learning.
Wei, Xian; Li, Yuanxiang; Shen, Hao; Chen, Fang; Kleinsteuber, Martin; Wang, Zhongfeng
2017-04-06
Video representation is an important and challenging task in the computer vision community. In this paper, we consider the problem of modeling and classifying video sequences of dynamic scenes which could be modeled in a dynamic textures (DT) framework. At first, we assume that image frames of a moving scene can be modeled as a Markov random process. We propose a sparse coding framework, named joint video dictionary learning (JVDL), to model a video adaptively. By treating the sparse coefficients of image frames over a learned dictionary as the underlying "states", we learn an efficient and robust linear transition matrix between two adjacent frames of sparse events in time series. Hence, a dynamic scene sequence is represented by an appropriate transition matrix associated with a dictionary. In order to ensure the stability of JVDL, we impose several constraints on such transition matrix and dictionary. The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames. Moreover, such learned JVDL parameters can be used for various DT applications, such as DT synthesis and recognition. Experimental results demonstrate the strong competitiveness of the proposed JVDL approach in comparison with state-of-the-art video representation methods. Especially, it performs significantly better in dealing with DT synthesis and recognition on heavily corrupted data.
Learning about the Dynamic Sun through Sounds
Quinn, M.; Peticolas, L. M.; Luhmann, J.; MacCallum, J.
2008-06-01
Can we hear the Sun or its solar wind? Not in the sense that they make sound. But we can take the particle, magnetic field, electric field, and image data and turn it into sound to demonstrate what the data tells us. We present work on turning data from the two-satellite NASA mission called STEREO (Solar TErrestrial RElations Observatory) into sounds and music (sonification). STEREO has two satellites orbiting the Sun near Earth's orbit to study the coronal mass ejections (CMEs) from the Corona. One sonification project aims to inspire musicians, museum patrons, and the public to learn more about CMEs by downloading STEREO data and using it to make music. We demonstrate the software and discuss the way in which it was developed. A second project aims to produce a museum exhibit using STEREO imagery and sounds from STEREO data. We demonstrate a "walk across the Sun" created for this exhibit so people can hear the features on solar images. We show how pixel intensity translates into pitches from selectable scales with selectable musical scale size and octave locations. We also share our successes and lessons learned.
Effects of noise on convergent game-learning dynamics
International Nuclear Information System (INIS)
Sanders, James B T; Galla, Tobias; Shapiro, Jonathan L
2012-01-01
We study stochastic effects on the lagging anchor dynamics, a reinforcement learning algorithm used to learn successful strategies in iterated games, which is known to converge to Nash points in the absence of noise. The dynamics is stochastic when players only have limited information about their opponents’ strategic propensities. The effects of this noise are studied analytically in the case where it is small but finite, and we show that the statistics and correlation properties of fluctuations can be computed to a high accuracy. We find that the system can exhibit quasicycles, driven by intrinsic noise. If players are asymmetric and use different parameters for their learning, a net payoff advantage can be achieved due to these stochastic oscillations around the deterministic equilibrium. (paper)
Directory of Open Access Journals (Sweden)
Chao Li
2017-02-01
Full Text Available Human gait, as a soft biometric, helps to recognize people through their walking. To further improve the recognition performance, we propose a novel video sensor-based gait representation, DeepGait, using deep convolutional features and introduce Joint Bayesian to model view variance. DeepGait is generated by using a pre-trained “very deep” network “D-Net” (VGG-D without any fine-tuning. For non-view setting, DeepGait outperforms hand-crafted representations (e.g., Gait Energy Image, Frequency-Domain Feature and Gait Flow Image, etc.. Furthermore, for cross-view setting, 256-dimensional DeepGait after PCA significantly outperforms the state-of-the-art methods on the OU-ISR large population (OULP dataset. The OULP dataset, which includes 4007 subjects, makes our result reliable in a statistically reliable way.
DEFF Research Database (Denmark)
Jensen, Finn Verner; Nielsen, Thomas Dyhre
2016-01-01
Mathematically, a Bayesian graphical model is a compact representation of the joint probability distribution for a set of variables. The most frequently used type of Bayesian graphical models are Bayesian networks. The structural part of a Bayesian graphical model is a graph consisting of nodes...
Directory of Open Access Journals (Sweden)
Chris Geremia
Full Text Available Epidemics of chronic wasting disease (CWD of North American Cervidae have potential to harm ecosystems and economies. We studied a migratory population of mule deer (Odocoileus hemionus affected by CWD for at least three decades using a Bayesian framework to integrate matrix population and disease models with long-term monitoring data and detailed process-level studies. We hypothesized CWD prevalence would be stable or increase between two observation periods during the late 1990s and after 2010, with higher CWD prevalence making deer population decline more likely. The weight of evidence suggested a reduction in the CWD outbreak over time, perhaps in response to intervening harvest-mediated population reductions. Disease effects on deer population growth under current conditions were subtle with a 72% chance that CWD depressed population growth. With CWD, we forecasted a growth rate near one and largely stable deer population. Disease effects appear to be moderated by timing of infection, prolonged disease course, and locally variable infection. Long-term outcomes will depend heavily on whether current conditions hold and high prevalence remains a localized phenomenon.
Najibi, N.; Lu, M.; Devineni, N.
2017-12-01
Long duration floods cause substantial damages and prolonged interruptions to water resource facilities and critical infrastructure. We present a novel generalized statistical and physical based model for flood duration with a deeper understanding of dynamically coupled nexus of the land surface wetness, effective atmospheric circulation and moisture transport/release. We applied the model on large reservoirs in the Missouri River Basin. The results indicate that the flood duration is not only a function of available moisture in the air, but also the antecedent condition of the blocking system of atmospheric pressure, resulting in enhanced moisture convergence, as well as the effectiveness of moisture condensation process leading to release. Quantifying these dynamics with a two-layer climate informed Bayesian multilevel model, we explain more than 80% variations in flood duration. The model considers the complex interaction between moisture transport, synoptic-to-large-scale atmospheric circulation pattern, and the antecedent wetness condition in the basin. Our findings suggest that synergy between a large low-pressure blocking system and a higher rate of divergent wind often triggers a long duration flood, and the prerequisite for moisture supply to trigger such event is moderate, which is more associated with magnitude than duration. In turn, this condition causes an extremely long duration flood if the surface wetness rate advancing to the flood event was already increased.
Machine learning molecular dynamics for the simulation of infrared spectra.
Gastegger, Michael; Behler, Jörg; Marquetand, Philipp
2017-10-01
Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects - typically neglected by conventional quantum chemistry approaches - we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potential approach of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the use of molecular forces during neural network potential training and the introduction of a fully automated sampling scheme. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n -alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all of these case studies we find an excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.
Path to Stochastic Stability: Comparative Analysis of Stochastic Learning Dynamics in Games
Jaleel, Hassan; Shamma, Jeff S.
2018-01-01
dynamics: Log-Linear Learning (LLL) and Metropolis Learning (ML). Although both of these dynamics have the same stochastically stable states, LLL and ML correspond to different behavioral models for decision making. Moreover, we demonstrate through
Woldegebriel, Michael; Zomer, Paul; Mol, Hans G J; Vivó-Truyols, Gabriel
2016-08-02
In this work, we introduce an automated, efficient, and elegant model to combine all pieces of evidence (e.g., expected retention times, peak shapes, isotope distributions, fragment-to-parent ratio) obtained from liquid chromatography-tandem mass spectrometry (LC-MS/MS/MS) data for screening purposes. Combining all these pieces of evidence requires a careful assessment of the uncertainties in the analytical system as well as all possible outcomes. To-date, the majority of the existing algorithms are highly dependent on user input parameters. Additionally, the screening process is tackled as a deterministic problem. In this work we present a Bayesian framework to deal with the combination of all these pieces of evidence. Contrary to conventional algorithms, the information is treated in a probabilistic way, and a final probability assessment of the presence/absence of a compound feature is computed. Additionally, all the necessary parameters except the chromatographic band broadening for the method are learned from the data in training and learning phase of the algorithm, avoiding the introduction of a large number of user-defined parameters. The proposed method was validated with a large data set and has shown improved sensitivity and specificity in comparison to a threshold-based commercial software package.
Kernel Bayesian ART and ARTMAP.
Masuyama, Naoki; Loo, Chu Kiong; Dawood, Farhan
2018-02-01
Adaptive Resonance Theory (ART) is one of the successful approaches to resolving "the plasticity-stability dilemma" in neural networks, and its supervised learning model called ARTMAP is a powerful tool for classification. Among several improvements, such as Fuzzy or Gaussian based models, the state of art model is Bayesian based one, while solving the drawbacks of others. However, it is known that the Bayesian approach for the high dimensional and a large number of data requires high computational cost, and the covariance matrix in likelihood becomes unstable. This paper introduces Kernel Bayesian ART (KBA) and ARTMAP (KBAM) by integrating Kernel Bayes' Rule (KBR) and Correntropy Induced Metric (CIM) to Bayesian ART (BA) and ARTMAP (BAM), respectively, while maintaining the properties of BA and BAM. The kernel frameworks in KBA and KBAM are able to avoid the curse of dimensionality. In addition, the covariance-free Bayesian computation by KBR provides the efficient and stable computational capability to KBA and KBAM. Furthermore, Correntropy-based similarity measurement allows improving the noise reduction ability even in the high dimensional space. The simulation experiments show that KBA performs an outstanding self-organizing capability than BA, and KBAM provides the superior classification ability than BAM, respectively. Copyright © 2017 Elsevier Ltd. All rights reserved.
Deep Learning with Dynamic Spiking Neurons and Fixed Feedback Weights.
Samadi, Arash; Lillicrap, Timothy P; Tweed, Douglas B
2017-03-01
Recent work in computer science has shown the power of deep learning driven by the backpropagation algorithm in networks of artificial neurons. But real neurons in the brain are different from most of these artificial ones in at least three crucial ways: they emit spikes rather than graded outputs, their inputs and outputs are related dynamically rather than by piecewise-smooth functions, and they have no known way to coordinate arrays of synapses in separate forward and feedback pathways so that they change simultaneously and identically, as they do in backpropagation. Given these differences, it is unlikely that current deep learning algorithms can operate in the brain, but we that show these problems can be solved by two simple devices: learning rules can approximate dynamic input-output relations with piecewise-smooth functions, and a variation on the feedback alignment algorithm can train deep networks without having to coordinate forward and feedback synapses. Our results also show that deep spiking networks learn much better if each neuron computes an intracellular teaching signal that reflects that cell's nonlinearity. With this mechanism, networks of spiking neurons show useful learning in synapses at least nine layers upstream from the output cells and perform well compared to other spiking networks in the literature on the MNIST digit recognition task.
Learning predictive statistics from temporal sequences: Dynamics and strategies.
Wang, Rui; Shen, Yuan; Tino, Peter; Welchman, Andrew E; Kourtzi, Zoe
2017-10-01
Human behavior is guided by our expectations about the future. Often, we make predictions by monitoring how event sequences unfold, even though such sequences may appear incomprehensible. Event structures in the natural environment typically vary in complexity, from simple repetition to complex probabilistic combinations. How do we learn these structures? Here we investigate the dynamics of structure learning by tracking human responses to temporal sequences that change in structure unbeknownst to the participants. Participants were asked to predict the upcoming item following a probabilistic sequence of symbols. Using a Markov process, we created a family of sequences, from simple frequency statistics (e.g., some symbols are more probable than others) to context-based statistics (e.g., symbol probability is contingent on preceding symbols). We demonstrate the dynamics with which individuals adapt to changes in the environment's statistics-that is, they extract the behaviorally relevant structures to make predictions about upcoming events. Further, we show that this structure learning relates to individual decision strategy; faster learning of complex structures relates to selection of the most probable outcome in a given context (maximizing) rather than matching of the exact sequence statistics. Our findings provide evidence for alternate routes to learning of behaviorally relevant statistics that facilitate our ability to predict future events in variable environments.
Neural dynamics of learning sound-action associations.
Directory of Open Access Journals (Sweden)
Adam McNamara
Full Text Available A motor component is pre-requisite to any communicative act as one must inherently move to communicate. To learn to make a communicative act, the brain must be able to dynamically associate arbitrary percepts to the neural substrate underlying the pre-requisite motor activity. We aimed to investigate whether brain regions involved in complex gestures (ventral pre-motor cortex, Brodmann Area 44 were involved in mediating association between novel abstract auditory stimuli and novel gestural movements. In a functional resonance imaging (fMRI study we asked participants to learn associations between previously unrelated novel sounds and meaningless gestures inside the scanner. We use functional connectivity analysis to eliminate the often present confound of 'strategic covert naming' when dealing with BA44 and to rule out effects of non-specific reductions in signal. Brodmann Area 44, a region incorporating Broca's region showed strong, bilateral, negative correlation of BOLD (blood oxygen level dependent response with learning of sound-action associations during data acquisition. Left-inferior-parietal-lobule (l-IPL and bilateral loci in and around visual area V5, right-orbital-frontal-gyrus, right-hippocampus, left-para-hippocampus, right-head-of-caudate, right-insula and left-lingual-gyrus also showed decreases in BOLD response with learning. Concurrent with these decreases in BOLD response, an increasing connectivity between areas of the imaged network as well as the right-middle-frontal-gyrus with rising learning performance was revealed by a psychophysiological interaction (PPI analysis. The increasing connectivity therefore occurs within an increasingly energy efficient network as learning proceeds. Strongest learning related connectivity between regions was found when analysing BA44 and l-IPL seeds. The results clearly show that BA44 and l-IPL is dynamically involved in linking gesture and sound and therefore provides evidence that one of
Lessons Learned From Dynamic Simulations of Advanced Fuel Cycles
International Nuclear Information System (INIS)
Piet, Steven J.; Dixon, Brent W.; Jacobson, Jacob J.; Matthern, Gretchen E.; Shropshire, David E.
2009-01-01
Years of performing dynamic simulations of advanced nuclear fuel cycle options provide insights into how they could work and how one might transition from the current once-through fuel cycle. This paper summarizes those insights from the context of the 2005 objectives and goals of the Advanced Fuel Cycle Initiative (AFCI). Our intent is not to compare options, assess options versus those objectives and goals, nor recommend changes to those objectives and goals. Rather, we organize what we have learned from dynamic simulations in the context of the AFCI objectives for waste management, proliferation resistance, uranium utilization, and economics. Thus, we do not merely describe 'lessons learned' from dynamic simulations but attempt to answer the 'so what' question by using this context. The analyses have been performed using the Verifiable Fuel Cycle Simulation of Nuclear Fuel Cycle Dynamics (VISION). We observe that the 2005 objectives and goals do not address many of the inherently dynamic discriminators among advanced fuel cycle options and transitions thereof
A self-learning algorithm for biased molecular dynamics
Tribello, Gareth A.; Ceriotti, Michele; Parrinello, Michele
2010-01-01
A new self-learning algorithm for accelerated dynamics, reconnaissance metadynamics, is proposed that is able to work with a very large number of collective coordinates. Acceleration of the dynamics is achieved by constructing a bias potential in terms of a patchwork of one-dimensional, locally valid collective coordinates. These collective coordinates are obtained from trajectory analyses so that they adapt to any new features encountered during the simulation. We show how this methodology can be used to enhance sampling in real chemical systems citing examples both from the physics of clusters and from the biological sciences. PMID:20876135
2nd Bayesian Young Statisticians Meeting
Bitto, Angela; Kastner, Gregor; Posekany, Alexandra
2015-01-01
The Second Bayesian Young Statisticians Meeting (BAYSM 2014) and the research presented here facilitate connections among researchers using Bayesian Statistics by providing a forum for the development and exchange of ideas. WU Vienna University of Business and Economics hosted BAYSM 2014 from September 18th to 19th. The guidance of renowned plenary lecturers and senior discussants is a critical part of the meeting and this volume, which follows publication of contributions from BAYSM 2013. The meeting's scientific program reflected the variety of fields in which Bayesian methods are currently employed or could be introduced in the future. Three brilliant keynote lectures by Chris Holmes (University of Oxford), Christian Robert (Université Paris-Dauphine), and Mike West (Duke University), were complemented by 24 plenary talks covering the major topics Dynamic Models, Applications, Bayesian Nonparametrics, Biostatistics, Bayesian Methods in Economics, and Models and Methods, as well as a lively poster session ...
Generation and Application of Virtual Dynamic Learning Environments
Directory of Open Access Journals (Sweden)
Esther Zaretsky
2009-04-01
Full Text Available The generation of virtual dynamic learning environments by mental imagery improved physical education of student teachers. Up-to-date studies showed that training computerized simulations improved spatial abilities, especially visualization of the body's movements in space, and enhanced academic achievements. The main program of the research concentrated on creating teaching units focusing on a variety of physical skills through computerized dynamic presentations. The findings showed that as the student teachers practiced the creation of simulations through the PowerPoint Software, it became clear to them how the computer is related to physical activities. Consequently their presentations became highly animated, and applied to the natural environment. The student teachers applied their presentations in their practical classroom and reported about their pupils' progress in physical skills. Moreover the motivation of the student teachers and pupils to both modes of learning, manipulating virtually and physically, was enhanced.
Creating Dynamic Learning Environment to Enhance Students’ Engagement in Learning Geometry
Sariyasa
2017-04-01
Learning geometry gives many benefits to students. It strengthens the development of deductive thinking and reasoning; it also provides an opportunity to improve visualisation and spatial ability. Some studies, however, have pointed out the difficulties that students encountered when learning geometry. A preliminary study by the author in Bali revealed that one of the main problems was teachers’ difficulties in delivering geometry instruction. It was partly due to the lack of appropriate instructional media. Coupling with dynamic geometry software, dynamic learning environments is a promising solution to this problem. Employing GeoGebra software supported by the well-designed instructional process may result in more meaningful learning, and consequently, students are motivated to engage in the learning process more deeply and actively. In this paper, we provide some examples of GeoGebra-aided learning activities that allow students to interactively explore and investigate geometry concepts and the properties of geometry objects. Thus, it is expected that such learning environment will enhance students’ internalisation process of geometry concepts.
Bayesian artificial intelligence
Korb, Kevin B
2010-01-01
Updated and expanded, Bayesian Artificial Intelligence, Second Edition provides a practical and accessible introduction to the main concepts, foundation, and applications of Bayesian networks. It focuses on both the causal discovery of networks and Bayesian inference procedures. Adopting a causal interpretation of Bayesian networks, the authors discuss the use of Bayesian networks for causal modeling. They also draw on their own applied research to illustrate various applications of the technology.New to the Second EditionNew chapter on Bayesian network classifiersNew section on object-oriente
Lewis, F L; Vamvoudakis, Kyriakos G
2011-02-01
Approximate dynamic programming (ADP) is a class of reinforcement learning methods that have shown their importance in a variety of applications, including feedback control of dynamical systems. ADP generally requires full information about the system internal states, which is usually not available in practical situations. In this paper, we show how to implement ADP methods using only measured input/output data from the system. Linear dynamical systems with deterministic behavior are considered herein, which are systems of great interest in the control system community. In control system theory, these types of methods are referred to as output feedback (OPFB). The stochastic equivalent of the systems dealt with in this paper is a class of partially observable Markov decision processes. We develop both policy iteration and value iteration algorithms that converge to an optimal controller that requires only OPFB. It is shown that, similar to Q -learning, the new methods have the important advantage that knowledge of the system dynamics is not needed for the implementation of these learning algorithms or for the OPFB control. Only the order of the system, as well as an upper bound on its "observability index," must be known. The learned OPFB controller is in the form of a polynomial autoregressive moving-average controller that has equivalent performance with the optimal state variable feedback gain.
The Self-Perception Theory vs. a Dynamic Learning Model
Swank, Otto H.
2006-01-01
Several economists have directed our attention to a finding in the social psychological literature that extrinsic motivation may undermine intrinsic motivation. The self-perception (SP) theory developed by Bem (1972) explains this finding. The crux of this theory is that people remember their past decisions and the extrinsic rewards they received, but they do not recall their intrinsic motives. In this paper I show that the SP theory can be modeled as a variant of a conventional dynamic learn...
Nursing students' learning dynamics and influencing factors in clinical contexts.
Lee, Jung Jae; Clarke, Charlotte L; Carson, Maggie N
2018-03-01
Clinical placements are essential for students to develop clinical skills to qualify as nurses. However, various difficulties encountered by nursing students during their clinical education detract from developing clinical competencies. This constructivist grounded theory study aims to explore nursing students' experiences in clinical nursing education, and to identify the factors that influence the clinical education students receive. Twenty-one individual and six group semi-structured interviews were conducted with sixteen fourth year nursing students and four registered nurses. This research identified six factors that influence nursing students' clinical education: interpersonal, socio-cultural, instructional, environmental, emotional and physical factors. The research has developed a dynamic model of learning in clinical contexts, which offers opportunities to understand how students' learning is influenced multifactorially during clinical placements. The understanding and application of the model can improve nursing instructional design, and subsequently, nursing students' learning in clinical contexts. Copyright © 2017 Elsevier Ltd. All rights reserved.
Online learning dynamics of multilayer perceptrons with unidentifiable parameters
Energy Technology Data Exchange (ETDEWEB)
Park, Hyeyoung [Laboratory for Mathematical Neuroscience, RIKEN Brain Science Institute, 2-1 Hirosawa, Wako, Saitama 351-0198 (Japan); Inoue, Masato [Laboratory for Mathematical Neuroscience, RIKEN Brain Science Institute, 2-1 Hirosawa, Wako, Saitama 351-0198 (Japan); Department of Otolaryngology, Head and Neck Surgery, Graduate School of Medicine, Kyoto University, Kyoto 606-8507 (Japan); ' Intelligent Cooperation and Control' , PRESTO, JST, c/o RIKEN BSI, Saitama 351-0198 (Japan); Okada, Masato [Laboratory for Mathematical Neuroscience, RIKEN Brain Science Institute, 2-1 Hirosawa, Wako, Saitama 351-0198 (Japan)
2003-11-28
In the over-realizable learning scenario of multilayer perceptrons, in which the student network has a larger number of hidden units than the true or optimal network, some of the weight parameters are unidentifiable. In this case, the teacher network consists of a union of optimal subspaces included in the parameter space. The optimal subspaces, which lead to singularities, are known to affect the estimation performance of neural networks. Using statistical mechanics, we investigate the online learning dynamics of two-layer neural networks in the over-realizable scenario with unidentifiable parameters. We show that the convergence speed strongly depends on the initial parameter conditions. We also show that there is a quasi-plateau around the optimal subspace, which differs from the well-known plateaus caused by permutation symmetry. In addition, we discuss the property of the final learning state, relating this to the singular structures.
Online learning dynamics of multilayer perceptrons with unidentifiable parameters
International Nuclear Information System (INIS)
Park, Hyeyoung; Inoue, Masato; Okada, Masato
2003-01-01
In the over-realizable learning scenario of multilayer perceptrons, in which the student network has a larger number of hidden units than the true or optimal network, some of the weight parameters are unidentifiable. In this case, the teacher network consists of a union of optimal subspaces included in the parameter space. The optimal subspaces, which lead to singularities, are known to affect the estimation performance of neural networks. Using statistical mechanics, we investigate the online learning dynamics of two-layer neural networks in the over-realizable scenario with unidentifiable parameters. We show that the convergence speed strongly depends on the initial parameter conditions. We also show that there is a quasi-plateau around the optimal subspace, which differs from the well-known plateaus caused by permutation symmetry. In addition, we discuss the property of the final learning state, relating this to the singular structures
Adaptive learning by extremal dynamics and negative feedback
International Nuclear Information System (INIS)
Bak, Per; Chialvo, Dante R.
2001-01-01
We describe a mechanism for biological learning and adaptation based on two simple principles: (i) Neuronal activity propagates only through the network's strongest synaptic connections (extremal dynamics), and (ii) the strengths of active synapses are reduced if mistakes are made, otherwise no changes occur (negative feedback). The balancing of those two tendencies typically shapes a synaptic landscape with configurations which are barely stable, and therefore highly flexible. This allows for swift adaptation to new situations. Recollection of past successes is achieved by punishing synapses which have once participated in activity associated with successful outputs much less than neurons that have never been successful. Despite its simplicity, the model can readily learn to solve complicated nonlinear tasks, even in the presence of noise. In particular, the learning time for the benchmark parity problem scales algebraically with the problem size N, with an exponent k∼1.4
Forecasting financial asset processes: stochastic dynamics via learning neural networks.
Giebel, S; Rainer, M
2010-01-01
Models for financial asset dynamics usually take into account their inherent unpredictable nature by including a suitable stochastic component into their process. Unknown (forward) values of financial assets (at a given time in the future) are usually estimated as expectations of the stochastic asset under a suitable risk-neutral measure. This estimation requires the stochastic model to be calibrated to some history of sufficient length in the past. Apart from inherent limitations, due to the stochastic nature of the process, the predictive power is also limited by the simplifying assumptions of the common calibration methods, such as maximum likelihood estimation and regression methods, performed often without weights on the historic time series, or with static weights only. Here we propose a novel method of "intelligent" calibration, using learning neural networks in order to dynamically adapt the parameters of the stochastic model. Hence we have a stochastic process with time dependent parameters, the dynamics of the parameters being themselves learned continuously by a neural network. The back propagation in training the previous weights is limited to a certain memory length (in the examples we consider 10 previous business days), which is similar to the maximal time lag of autoregressive processes. We demonstrate the learning efficiency of the new algorithm by tracking the next-day forecasts for the EURTRY and EUR-HUF exchange rates each.
Nassar, Matthew R.; Wilson, Robert C.; Heasly, Benjamin; Gold, Joshua I.
2010-01-01
Maintaining appropriate beliefs about variables needed for effective decision-making can be difficult in a dynamic environment. One key issue is the amount of influence that unexpected outcomes should have on existing beliefs. In general, outcomes that are unexpected because of a fundamental change in the environment should carry more influence than outcomes that are unexpected because of persistent environmental stochasticity. Here we use a novel task to characterize how well human subjects ...
Bayesian Modeling of a Human MMORPG Player
Synnaeve, Gabriel; Bessière, Pierre
2011-03-01
This paper describes an application of Bayesian programming to the control of an autonomous avatar in a multiplayer role-playing game (the example is based on World of Warcraft). We model a particular task, which consists of choosing what to do and to select which target in a situation where allies and foes are present. We explain the model in Bayesian programming and show how we could learn the conditional probabilities from data gathered during human-played sessions.
Dynamic Scaffolding of Socially Regulated Learning in a Computer-Based Learning Environment
Molenaar, Inge; Roda, Claudia; van Boxtel, Carla; Sleegers, Peter
2012-01-01
The aim of this study is to test the effects of dynamically scaffolding social regulation of middle school students working in a computer-based learning environment. Dyads in the scaffolding condition (N=56) are supported with computer-generated scaffolds and students in the control condition (N=54) do not receive scaffolds. The scaffolds are…
Dynamic Scaffolding of Socially Regulated Learning in a Computer-Based Learning Environment
Molenaar, I.; Roda, Claudia; van Boxtel, Carla A.M.; Sleegers, P.J.C.
2012-01-01
The aim of this study is to test the effects of dynamically scaffolding social regulation of middle school students working in a computer-based learning environment. Dyads in the scaffolding condition (N = 56) are supported with computer-generated scaffolds and students in the control condition (N =
Ludolph, Nicolas; Giese, Martin A; Ilg, Winfried
2017-10-16
There is increasing evidence that sensorimotor learning under real-life conditions relies on a composition of several learning processes. Nevertheless, most studies examine learning behaviour in relation to one specific learning mechanism. In this study, we examined the interaction between reward-based skill acquisition and motor adaptation to changes of object dynamics. Thirty healthy subjects, split into two groups, acquired the skill of balancing a pole on a cart in virtual reality. In one group, we gradually increased the gravity, making the task easier in the beginning and more difficult towards the end. In the second group, subjects had to acquire the skill on the maximum, most difficult gravity level. We hypothesized that the gradual increase in gravity during skill acquisition supports learning despite the necessary adjustments to changes in cart-pole dynamics. We found that the gradual group benefits from the slow increment, although overall improvement was interrupted by the changes in gravity and resulting system dynamics, which caused short-term degradations in performance and timing of actions. In conclusion, our results deliver evidence for an interaction of reward-based skill acquisition and motor adaptation processes, which indicates the importance of both processes for the development of optimized skill acquisition schedules.
Reconstructing Interlaced High-Dynamic-Range Video Using Joint Learning.
Inchang Choi; Seung-Hwan Baek; Kim, Min H
2017-11-01
For extending the dynamic range of video, it is a common practice to capture multiple frames sequentially with different exposures and combine them to extend the dynamic range of each video frame. However, this approach results in typical ghosting artifacts due to fast and complex motion in nature. As an alternative, video imaging with interlaced exposures has been introduced to extend the dynamic range. However, the interlaced approach has been hindered by jaggy artifacts and sensor noise, leading to concerns over image quality. In this paper, we propose a data-driven approach for jointly solving two specific problems of deinterlacing and denoising that arise in interlaced video imaging with different exposures. First, we solve the deinterlacing problem using joint dictionary learning via sparse coding. Since partial information of detail in differently exposed rows is often available via interlacing, we make use of the information to reconstruct details of the extended dynamic range from the interlaced video input. Second, we jointly solve the denoising problem by tailoring sparse coding to better handle additive noise in low-/high-exposure rows, and also adopt multiscale homography flow to temporal sequences for denoising. We anticipate that the proposed method will allow for concurrent capture of higher dynamic range video frames without suffering from ghosting artifacts. We demonstrate the advantages of our interlaced video imaging compared with the state-of-the-art high-dynamic-range video methods.
Visual recognition and inference using dynamic overcomplete sparse learning.
Murray, Joseph F; Kreutz-Delgado, Kenneth
2007-09-01
We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and expectation-driven segmentation. Using properties of biological vision for guidance, we posit a stochastic generative world model and from it develop a simplified world model (SWM) based on a tractable variational approximation that is designed to enforce sparse coding. Recent developments in computational methods for learning overcomplete representations (Lewicki & Sejnowski, 2000; Teh, Welling, Osindero, & Hinton, 2003) suggest that overcompleteness can be useful for visual tasks, and we use an overcomplete dictionary learning algorithm (Kreutz-Delgado, et al., 2003) as a preprocessing stage to produce accurate, sparse codings of images. Inference is performed by constructing a dynamic multilayer network with feedforward, feedback, and lateral connections, which is trained to approximate the SWM. Learning is done with a variant of the back-propagation-through-time algorithm, which encourages convergence to desired states within a fixed number of iterations. Vision tasks require large networks, and to make learning efficient, we take advantage of the sparsity of each layer to update only a small subset of elements in a large weight matrix at each iteration. Experiments on a set of rotated objects demonstrate various types of visual inference and show that increasing the degree of overcompleteness improves recognition performance in difficult scenes with occluded objects in clutter.
Adaptation and learning: characteristic time scales of performance dynamics.
Newell, Karl M; Mayer-Kress, Gottfried; Hong, S Lee; Liu, Yeou-Teh
2009-12-01
A multiple time scales landscape model is presented that reveals structures of performance dynamics that were not resolved in the traditional power law analysis of motor learning. It shows the co-existence of separate processes during and between practice sessions that evolve in two independent dimensions characterized by time scales that differ by about an order of magnitude. Performance along the slow persistent dimension of learning improves often as much and sometimes more during rest (memory consolidation and/or insight generation processes) than during a practice session itself. In contrast, the process characterized by the fast, transient dimension of adaptation reverses direction between practice sessions, thereby significantly degrading performance at the beginning of the next practice session (warm-up decrement). The theoretical model fits qualitatively and quantitatively the data from Snoddy's [Snoddy, G. S. (1926). Learning and stability. Journal of Applied Psychology, 10, 1-36] classic learning study of mirror tracing and other averaged and individual data sets, and provides a new account of the processes of change in adaptation and learning. 2009 Elsevier B.V. All rights reserved.
Modeling Women's Menstrual Cycles using PICI Gates in Bayesian Network.
Zagorecki, Adam; Łupińska-Dubicka, Anna; Voortman, Mark; Druzdzel, Marek J
2016-03-01
A major difficulty in building Bayesian network (BN) models is the size of conditional probability tables, which grow exponentially in the number of parents. One way of dealing with this problem is through parametric conditional probability distributions that usually require only a number of parameters that is linear in the number of parents. In this paper, we introduce a new class of parametric models, the Probabilistic Independence of Causal Influences (PICI) models, that aim at lowering the number of parameters required to specify local probability distributions, but are still capable of efficiently modeling a variety of interactions. A subset of PICI models is decomposable and this leads to significantly faster inference as compared to models that cannot be decomposed. We present an application of the proposed method to learning dynamic BNs for modeling a woman's menstrual cycle. We show that PICI models are especially useful for parameter learning from small data sets and lead to higher parameter accuracy than when learning CPTs.
Balanced sensitivity functions for tuning multi-dimensional Bayesian network classifiers
Bolt, J.H.; van der Gaag, L.C.
Multi-dimensional Bayesian network classifiers are Bayesian networks of restricted topological structure, which are tailored to classifying data instances into multiple dimensions. Like more traditional classifiers, multi-dimensional classifiers are typically learned from data and may include
Yuan, Ying; MacKinnon, David P.
2009-01-01
This article proposes Bayesian analysis of mediation effects. Compared to conventional frequentist mediation analysis, the Bayesian approach has several advantages. First, it allows researchers to incorporate prior information into the mediation analysis, thus potentially improving the efficiency of estimates. Second, under the Bayesian mediation analysis, inference is straightforward and exact, which makes it appealing for studies with small samples. Third, the Bayesian approach is conceptua...
Marsman, M.; Wagenmakers, E.-J.
2017-01-01
We illustrate the Bayesian approach to data analysis using the newly developed statistical software program JASP. With JASP, researchers are able to take advantage of the benefits that the Bayesian framework has to offer in terms of parameter estimation and hypothesis testing. The Bayesian
Bayesian estimation inherent in a Mexican-hat-type neural network
Takiyama, Ken
2016-05-01
Brain functions, such as perception, motor control and learning, and decision making, have been explained based on a Bayesian framework, i.e., to decrease the effects of noise inherent in the human nervous system or external environment, our brain integrates sensory and a priori information in a Bayesian optimal manner. However, it remains unclear how Bayesian computations are implemented in the brain. Herein, I address this issue by analyzing a Mexican-hat-type neural network, which was used as a model of the visual cortex, motor cortex, and prefrontal cortex. I analytically demonstrate that the dynamics of an order parameter in the model corresponds exactly to a variational inference of a linear Gaussian state-space model, a Bayesian estimation, when the strength of recurrent synaptic connectivity is appropriately stronger than that of an external stimulus, a plausible condition in the brain. This exact correspondence can reveal the relationship between the parameters in the Bayesian estimation and those in the neural network, providing insight for understanding brain functions.
MCMC for parameters estimation by bayesian approach
International Nuclear Information System (INIS)
Ait Saadi, H.; Ykhlef, F.; Guessoum, A.
2011-01-01
This article discusses the parameter estimation for dynamic system by a Bayesian approach associated with Markov Chain Monte Carlo methods (MCMC). The MCMC methods are powerful for approximating complex integrals, simulating joint distributions, and the estimation of marginal posterior distributions, or posterior means. The MetropolisHastings algorithm has been widely used in Bayesian inference to approximate posterior densities. Calibrating the proposal distribution is one of the main issues of MCMC simulation in order to accelerate the convergence.
Directory of Open Access Journals (Sweden)
Georgiana-Alina Ionita
2016-10-01
Full Text Available The paper proposes the analysis of the main drivers of the economic growth in Central and Eastern Europe, in three emerging countries: Czech Republic, Hungary and Poland, with a development stage similar with that of Romania. Given the vulnerabilities of the Central and Eastern Europe region at the beginning and during the recent global economic and financial crisis, there is an increased interest to identify the models that can describe the principalcharacteristics of the Central and Eastern Europe macroeconomic variables: gross domestic product, investment, wages and salaries, inflation, hours worked, consumption and themonetary variable- interest rate. Moreover, another scope is to analyze the frictions that describe the evolution of the seven data series, as the stochastic dynamic of the macroeconomic model is driven by orthogonal structural shocks.
Exploiting the Dynamics of Soft Materials for Machine Learning.
Nakajima, Kohei; Hauser, Helmut; Li, Tao; Pfeifer, Rolf
2018-06-01
Soft materials are increasingly utilized for various purposes in many engineering applications. These materials have been shown to perform a number of functions that were previously difficult to implement using rigid materials. Here, we argue that the diverse dynamics generated by actuating soft materials can be effectively used for machine learning purposes. This is demonstrated using a soft silicone arm through a technique of multiplexing, which enables the rich transient dynamics of the soft materials to be fully exploited as a computational resource. The computational performance of the soft silicone arm is examined through two standard benchmark tasks. Results show that the soft arm compares well to or even outperforms conventional machine learning techniques under multiple conditions. We then demonstrate that this system can be used for the sensory time series prediction problem for the soft arm itself, which suggests its immediate applicability to a real-world machine learning problem. Our approach, on the one hand, represents a radical departure from traditional computational methods, whereas on the other hand, it fits nicely into a more general perspective of computation by way of exploiting the properties of physical materials in the real world.
Group performance and group learning at dynamic system control tasks
International Nuclear Information System (INIS)
Drewes, Sylvana
2013-01-01
Proper management of dynamic systems (e.g. cooling systems of nuclear power plants or production and warehousing) is important to ensure public safety and economic success. So far, research has provided broad evidence for systematic shortcomings in individuals' control performance of dynamic systems. This research aims to investigate whether groups manifest synergy (Larson, 2010) and outperform individuals and if so, what processes lead to these performance advantages. In three experiments - including simulations of a nuclear power plant and a business setting - I compare the control performance of three-person-groups to the average individual performance and to nominal groups (N = 105 groups per experiment). The nominal group condition captures the statistical advantage of aggregated group judgements not due to social interaction. First, results show a superior performance of groups compared to individuals. Second, a meta-analysis across all three experiments shows interaction-based process gains in dynamic control tasks: Interacting groups outperform the average individual performance as well as the nominal group performance. Third, group interaction leads to stable individual improvements of group members that exceed practice effects. In sum, these results provide the first unequivocal evidence for interaction-based performance gains of groups in dynamic control tasks and imply that employers should rely on groups to provide opportunities for individual learning and to foster dynamic system control at its best.
International Nuclear Information System (INIS)
Rajabalinejad, M.
2010-01-01
To reduce cost of Monte Carlo (MC) simulations for time-consuming processes, Bayesian Monte Carlo (BMC) is introduced in this paper. The BMC method reduces number of realizations in MC according to the desired accuracy level. BMC also provides a possibility of considering more priors. In other words, different priors can be integrated into one model by using BMC to further reduce cost of simulations. This study suggests speeding up the simulation process by considering the logical dependence of neighboring points as prior information. This information is used in the BMC method to produce a predictive tool through the simulation process. The general methodology and algorithm of BMC method are presented in this paper. The BMC method is applied to the simplified break water model as well as the finite element model of 17th Street Canal in New Orleans, and the results are compared with the MC and Dynamic Bounds methods.
Experiential Learning as a Constraint-Led Process: An Ecological Dynamics Perspective
Brymer, Eric; Davids, Keith
2014-01-01
In this paper we present key ideas for an ecological dynamics approach to learning that reveal the importance of learner-environment interactions to frame outdoor experiential learning. We propose that ecological dynamics provides a useful framework for understanding the interacting constraints of the learning process and for designing learning…
Concurrent Dynamics of Category Learning and Metacognitive Judgments
Directory of Open Access Journals (Sweden)
Valnea Žauhar
2016-09-01
Full Text Available In two experiments, we examined the correspondence between the dynamics of metacognitive judgments and classification accuracy when participants were asked to learn category structures of different levels of complexity, i.e., to learn tasks of types I, II and III according to Shepard, Hovland, and Jenkins (1961. The stimuli were simple geometrical figures varying in the following three dimensions: color, shape, and size. In Experiment 1, we found moderate positive correlations between confidence and accuracy in task type II and weaker correlation in task type I and III. Moreover, the trend analysis in the backward learning curves revealed that there is a non-linear trend in accuracy for all three task types, but the same trend was observed in confidence for the task type I and II but not for task type III. In Experiment 2, we found that the feeling-of-warmth judgments (FOWs showed moderate positive correlation with accuracy in all task types. Trend analysis revealed a similar non-linear component in accuracy and metacognitive judgments in task type II and III but not in task type I. Our results suggest that FOWs are a more sensitive measure of the progress of learning than confidence because FOWs capture global knowledge about the category structure, while confidence judgments are given at the level of an individual exemplar.
Huang, Xiaodong; Clements, Archie C A; Williams, Gail; Mengersen, Kerrie; Tong, Shilu; Hu, Wenbiao
2016-04-01
A pandemic strain of influenza A spread rapidly around the world in 2009, now referred to as pandemic (H1N1) 2009. This study aimed to examine the spatiotemporal variation in the transmission rate of pandemic (H1N1) 2009 associated with changes in local socio-environmental conditions from May 7-December 31, 2009, at a postal area level in Queensland, Australia. We used the data on laboratory-confirmed H1N1 cases to examine the spatiotemporal dynamics of transmission using a flexible Bayesian, space-time, Susceptible-Infected-Recovered (SIR) modelling approach. The model incorporated parameters describing spatiotemporal variation in H1N1 infection and local socio-environmental factors. The weekly transmission rate of pandemic (H1N1) 2009 was negatively associated with the weekly area-mean maximum temperature at a lag of 1 week (LMXT) (posterior mean: -0.341; 95% credible interval (CI): -0.370--0.311) and the socio-economic index for area (SEIFA) (posterior mean: -0.003; 95% CI: -0.004--0.001), and was positively associated with the product of LMXT and the weekly area-mean vapour pressure at a lag of 1 week (LVAP) (posterior mean: 0.008; 95% CI: 0.007-0.009). There was substantial spatiotemporal variation in transmission rate of pandemic (H1N1) 2009 across Queensland over the epidemic period. High random effects of estimated transmission rates were apparent in remote areas and some postal areas with higher proportion of indigenous populations and smaller overall populations. Local SEIFA and local atmospheric conditions were associated with the transmission rate of pandemic (H1N1) 2009. The more populated regions displayed consistent and synchronized epidemics with low average transmission rates. The less populated regions had high average transmission rates with more variations during the H1N1 epidemic period. Copyright © 2016 Elsevier Inc. All rights reserved.
Nassar, Matthew R; Wilson, Robert C; Heasly, Benjamin; Gold, Joshua I
2010-09-15
Maintaining appropriate beliefs about variables needed for effective decision making can be difficult in a dynamic environment. One key issue is the amount of influence that unexpected outcomes should have on existing beliefs. In general, outcomes that are unexpected because of a fundamental change in the environment should carry more influence than outcomes that are unexpected because of persistent environmental stochasticity. Here we use a novel task to characterize how well human subjects follow these principles under a range of conditions. We show that the influence of an outcome depends on both the error made in predicting that outcome and the number of similar outcomes experienced previously. We also show that the exact nature of these tendencies varies considerably across subjects. Finally, we show that these patterns of behavior are consistent with a computationally simple reduction of an ideal-observer model. The model adjusts the influence of newly experienced outcomes according to ongoing estimates of uncertainty and the probability of a fundamental change in the process by which outcomes are generated. A prior that quantifies the expected frequency of such environmental changes accounts for individual variability, including a positive relationship between subjective certainty and the degree to which new information influences existing beliefs. The results suggest that the brain adaptively regulates the influence of decision outcomes on existing beliefs using straightforward updating rules that take into account both recent outcomes and prior expectations about higher-order environmental structure.
Illuminating the Effects of Dynamic Lighting on Student Learning
Directory of Open Access Journals (Sweden)
Michael S. Mott
2012-05-01
Full Text Available Light is universally understood as essential to the human condition. Yet light quality varies substantially in nature and in controlled environments leading to questions of which artificial light characteristics facilitate maximum learning. Recent research has examined lighting variables of color temperature, and illumination for affecting sleep, mood, focus, motivation, concentration, and work and school performance. This has resulted in artificial light systems intended to support human beings in their actualization through dynamic lighting technology allowing for different lighting conditions per task. A total of 84 third graders were exposed to either focus (6000K-100fc average maintained or normal lighting. Focus lighting led to a higher percentage increase in oral reading fluency performance (36% than did control lighting (17%. No lighting effects were found for motivation or concentration, possibly attributable to the younger age level of respondents as compared with European studies. These findings illuminate the need for further research on artificial light and learning.
Bio-Inspired Neural Model for Learning Dynamic Models
Duong, Tuan; Duong, Vu; Suri, Ronald
2009-01-01
A neural-network mathematical model that, relative to prior such models, places greater emphasis on some of the temporal aspects of real neural physical processes, has been proposed as a basis for massively parallel, distributed algorithms that learn dynamic models of possibly complex external processes by means of learning rules that are local in space and time. The algorithms could be made to perform such functions as recognition and prediction of words in speech and of objects depicted in video images. The approach embodied in this model is said to be "hardware-friendly" in the following sense: The algorithms would be amenable to execution by special-purpose computers implemented as very-large-scale integrated (VLSI) circuits that would operate at relatively high speeds and low power demands.
Reversal Learning in Humans and Gerbils: Dynamic Control Network Facilitates Learning.
Jarvers, Christian; Brosch, Tobias; Brechmann, André; Woldeit, Marie L; Schulz, Andreas L; Ohl, Frank W; Lommerzheim, Marcel; Neumann, Heiko
2016-01-01
Biologically plausible modeling of behavioral reinforcement learning tasks has seen great improvements over the past decades. Less work has been dedicated to tasks involving contingency reversals, i.e., tasks in which the original behavioral goal is reversed one or multiple times. The ability to adjust to such reversals is a key element of behavioral flexibility. Here, we investigate the neural mechanisms underlying contingency-reversal tasks. We first conduct experiments with humans and gerbils to demonstrate memory effects, including multiple reversals in which subjects (humans and animals) show a faster learning rate when a previously learned contingency re-appears. Motivated by recurrent mechanisms of learning and memory for object categories, we propose a network architecture which involves reinforcement learning to steer an orienting system that monitors the success in reward acquisition. We suggest that a model sensory system provides feature representations which are further processed by category-related subnetworks which constitute a neural analog of expert networks. Categories are selected dynamically in a competitive field and predict the expected reward. Learning occurs in sequentialized phases to selectively focus the weight adaptation to synapses in the hierarchical network and modulate their weight changes by a global modulator signal. The orienting subsystem itself learns to bias the competition in the presence of continuous monotonic reward accumulation. In case of sudden changes in the discrepancy of predicted and acquired reward the activated motor category can be switched. We suggest that this subsystem is composed of a hierarchically organized network of dis-inhibitory mechanisms, dubbed a dynamic control network (DCN), which resembles components of the basal ganglia. The DCN selectively activates an expert network, corresponding to the current behavioral strategy. The trace of the accumulated reward is monitored such that large sudden
Research of Dynamic Competitive Learning in Neural Networks
Institute of Scientific and Technical Information of China (English)
PAN Hao; CEN Li; ZHONG Luo
2005-01-01
Introduce a method of generation of new units within a cluster and a algorithm of generating new clusters.The model automatically builds up its dynamically growing internal representation structure during the learning process.Comparing model with other typical classification algorithm such as the Kohonen's self-organizing map, the model realizes a multilevel classification of the input pattern with an op tional accuracy and gives a strong support possibility for the parallel computational main processor. The idea is suitable for the high level storage of complex datas struetures for object recognition.
Harnessing Disordered-Ensemble Quantum Dynamics for Machine Learning
Fujii, Keisuke; Nakajima, Kohei
2017-08-01
The quantum computer has an amazing potential of fast information processing. However, the realization of a digital quantum computer is still a challenging problem requiring highly accurate controls and key application strategies. Here we propose a platform, quantum reservoir computing, to solve these issues successfully by exploiting the natural quantum dynamics of ensemble systems, which are ubiquitous in laboratories nowadays, for machine learning. This framework enables ensemble quantum systems to universally emulate nonlinear dynamical systems including classical chaos. A number of numerical experiments show that quantum systems consisting of 5-7 qubits possess computational capabilities comparable to conventional recurrent neural networks of 100-500 nodes. This discovery opens up a paradigm for information processing with artificial intelligence powered by quantum physics.
Learning Human Actions by Combining Global Dynamics and Local Appearance.
Luo, Guan; Yang, Shuang; Tian, Guodong; Yuan, Chunfeng; Hu, Weiming; Maybank, Stephen J
2014-12-01
In this paper, we address the problem of human action recognition through combining global temporal dynamics and local visual spatio-temporal appearance features. For this purpose, in the global temporal dimension, we propose to model the motion dynamics with robust linear dynamical systems (LDSs) and use the model parameters as motion descriptors. Since LDSs live in a non-Euclidean space and the descriptors are in non-vector form, we propose a shift invariant subspace angles based distance to measure the similarity between LDSs. In the local visual dimension, we construct curved spatio-temporal cuboids along the trajectories of densely sampled feature points and describe them using histograms of oriented gradients (HOG). The distance between motion sequences is computed with the Chi-Squared histogram distance in the bag-of-words framework. Finally we perform classification using the maximum margin distance learning method by combining the global dynamic distances and the local visual distances. We evaluate our approach for action recognition on five short clips data sets, namely Weizmann, KTH, UCF sports, Hollywood2 and UCF50, as well as three long continuous data sets, namely VIRAT, ADL and CRIM13. We show competitive results as compared with current state-of-the-art methods.
Directory of Open Access Journals (Sweden)
Ulrich Dettweiler
2017-12-01
Full Text Available Research has shown that outdoor educational interventions can lead to students' increased self-regulated motivational behavior. In this study, we searched into the satisfaction of basic psychological needs (BPN, i.e., autonomy support, the learners' experience of competence, and relatedness, both within the peer group and with their teachers, through outdoor learning. From 2014 to 2016, n = 281 students attended “research weeks” at a Student Science Lab in the Alpine National Park Berchtesgaden (Germany. The program is a curriculum-based one-week residential course, centered on a 2-day research expedition. Both before and after the course, students completed a composite questionnaire addressing BPN-satisfaction and overall motivational behavior in relation to the Self-Determination Index (SDI. At the latter time-point, students also reported on their experiences during the intervention. Questionnaire data was analyzed using a set of Bayesian General Linear Models with random effects. Those quantitative measures have been complemented by and contextualized with a set of qualitative survey methods. The results showed that the basic psychological needs influence the motivational behavior in both contexts equally, however on different scale levels. The basic needs satisfaction in the outdoor context is decisively higher than indoors. Moreover, the increment of competence-experience from the school context to the hands-on outdoor program appears to have the biggest impact to students' increased intrinsic motivation during the intervention. Increased autonomy support, student-teacher relations, and student-student relations have much less or no influence on the overall difference of motivational behavior. Gender does not influence the results. The contextualization partly supports those results and provide further explanation for the students' increased self-regulation in the outdoors. They add some explanatory thrust to the argument that outdoor
Machine learning control taming nonlinear dynamics and turbulence
Duriez, Thomas; Noack, Bernd R
2017-01-01
This is the first book on a generally applicable control strategy for turbulence and other complex nonlinear systems. The approach of the book employs powerful methods of machine learning for optimal nonlinear control laws. This machine learning control (MLC) is motivated and detailed in Chapters 1 and 2. In Chapter 3, methods of linear control theory are reviewed. In Chapter 4, MLC is shown to reproduce known optimal control laws for linear dynamics (LQR, LQG). In Chapter 5, MLC detects and exploits a strongly nonlinear actuation mechanism of a low-dimensional dynamical system when linear control methods are shown to fail. Experimental control demonstrations from a laminar shear-layer to turbulent boundary-layers are reviewed in Chapter 6, followed by general good practices for experiments in Chapter 7. The book concludes with an outlook on the vast future applications of MLC in Chapter 8. Matlab codes are provided for easy reproducibility of the presented results. The book includes interviews with leading r...
A Reinforcement Learning Framework for Spiking Networks with Dynamic Synapses
Directory of Open Access Journals (Sweden)
Karim El-Laithy
2011-01-01
Full Text Available An integration of both the Hebbian-based and reinforcement learning (RL rules is presented for dynamic synapses. The proposed framework permits the Hebbian rule to update the hidden synaptic model parameters regulating the synaptic response rather than the synaptic weights. This is performed using both the value and the sign of the temporal difference in the reward signal after each trial. Applying this framework, a spiking network with spike-timing-dependent synapses is tested to learn the exclusive-OR computation on a temporally coded basis. Reward values are calculated with the distance between the output spike train of the network and a reference target one. Results show that the network is able to capture the required dynamics and that the proposed framework can reveal indeed an integrated version of Hebbian and RL. The proposed framework is tractable and less computationally expensive. The framework is applicable to a wide class of synaptic models and is not restricted to the used neural representation. This generality, along with the reported results, supports adopting the introduced approach to benefit from the biologically plausible synaptic models in a wide range of intuitive signal processing.
MapReduce Based Parallel Bayesian Network for Manufacturing Quality Control
Zheng, Mao-Kuan; Ming, Xin-Guo; Zhang, Xian-Yu; Li, Guo-Ming
2017-09-01
Increasing complexity of industrial products and manufacturing processes have challenged conventional statistics based quality management approaches in the circumstances of dynamic production. A Bayesian network and big data analytics integrated approach for manufacturing process quality analysis and control is proposed. Based on Hadoop distributed architecture and MapReduce parallel computing model, big volume and variety quality related data generated during the manufacturing process could be dealt with. Artificial intelligent algorithms, including Bayesian network learning, classification and reasoning, are embedded into the Reduce process. Relying on the ability of the Bayesian network in dealing with dynamic and uncertain problem and the parallel computing power of MapReduce, Bayesian network of impact factors on quality are built based on prior probability distribution and modified with posterior probability distribution. A case study on hull segment manufacturing precision management for ship and offshore platform building shows that computing speed accelerates almost directly proportionally to the increase of computing nodes. It is also proved that the proposed model is feasible for locating and reasoning of root causes, forecasting of manufacturing outcome, and intelligent decision for precision problem solving. The integration of bigdata analytics and BN method offers a whole new perspective in manufacturing quality control.
Sparse Event Modeling with Hierarchical Bayesian Kernel Methods
2016-01-05
SECURITY CLASSIFICATION OF: The research objective of this proposal was to develop a predictive Bayesian kernel approach to model count data based on...several predictive variables. Such an approach, which we refer to as the Poisson Bayesian kernel model, is able to model the rate of occurrence of... kernel methods made use of: (i) the Bayesian property of improving predictive accuracy as data are dynamically obtained, and (ii) the kernel function
Genetic algorithm enhanced by machine learning in dynamic aperture optimization
Li, Yongjun; Cheng, Weixing; Yu, Li Hua; Rainer, Robert
2018-05-01
With the aid of machine learning techniques, the genetic algorithm has been enhanced and applied to the multi-objective optimization problem presented by the dynamic aperture of the National Synchrotron Light Source II (NSLS-II) Storage Ring. During the evolution processes employed by the genetic algorithm, the population is classified into different clusters in the search space. The clusters with top average fitness are given "elite" status. Intervention on the population is implemented by repopulating some potentially competitive candidates based on the experience learned from the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is therefore improved while diversity is not lost. Maintaining diversity ensures that the optimization is global rather than local. The quality of the population increases and produces more competitive descendants accelerating the evolution process significantly. When identifying the distribution of optimal candidates, they appear to be located in isolated islands within the search space. Some of these optimal candidates have been experimentally confirmed at the NSLS-II storage ring. The machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm.
Relating Cortical Wave Dynamics to Learning and Remembering
Directory of Open Access Journals (Sweden)
Eduardo Mercado III
2014-12-01
Full Text Available Electrical waves propagate across sensory and motor cortices in stereotypical patterns. These waves have been described as potentially facilitating sensory processing when they travel through sensory cortex, as guiding movement preparation and performance when they travel across motor cortex, and as possibly promoting synaptic plasticity and the consolidation of memory traces, especially during sleep. Here, an alternative theoretical framework is suggested that integrates Pavlovian hypotheses about learning and cortical function with concepts from contemporary proceduralist theories of memory. The proposed framework postulates that sensory-evoked cortical waves are gradually modified across repeated experiences such that the waves more effectively differentiate sensory events, and so that the waves are more likely to reverberate. It is argued that the qualities of cortical waves—their origins, form, intensity, speed, periodicity, extent, and trajectories —are a function of both the structural organization of neural circuits and ongoing reverberations resulting from previously experienced events. It is hypothesized that experience-dependent cortical plasticity, both in the short- and long-term, modulates the qualities of cortical waves, thereby enabling individuals to make progressively more precise distinctions between complex sensory events, and to reconstruct components of previously experienced events. Unlike most current neurobiological theories of learning and memory mechanisms, this hypothesis does not assume that synaptic plasticity, or any other form of neural plasticity, serves to store physical records of previously experienced events for later reactivation. Rather, the reorganization of cortical circuits may alter the potential for certain wave patterns to arise and persist. Understanding what factors determine the spatiotemporal dynamics of cortical waves, how structural changes affect their qualities, and how wave dynamics
Applications of Bayesian decision theory to intelligent tutoring systems
Vos, Hendrik J.
1994-01-01
Some applications of Bayesian decision theory to intelligent tutoring systems are considered. How the problem of adapting the appropriate amount of instruction to the changing nature of a student's capabilities during the learning process can be situated in the general framework of Bayesian decision
Seeded Bayesian Networks: Constructing genetic networks from microarray data
Directory of Open Access Journals (Sweden)
Quackenbush John
2008-07-01
Full Text Available Abstract Background DNA microarrays and other genomics-inspired technologies provide large datasets that often include hidden patterns of correlation between genes reflecting the complex processes that underlie cellular metabolism and physiology. The challenge in analyzing large-scale expression data has been to extract biologically meaningful inferences regarding these processes – often represented as networks – in an environment where the datasets are often imperfect and biological noise can obscure the actual signal. Although many techniques have been developed in an attempt to address these issues, to date their ability to extract meaningful and predictive network relationships has been limited. Here we describe a method that draws on prior information about gene-gene interactions to infer biologically relevant pathways from microarray data. Our approach consists of using preliminary networks derived from the literature and/or protein-protein interaction data as seeds for a Bayesian network analysis of microarray results. Results Through a bootstrap analysis of gene expression data derived from a number of leukemia studies, we demonstrate that seeded Bayesian Networks have the ability to identify high-confidence gene-gene interactions which can then be validated by comparison to other sources of pathway data. Conclusion The use of network seeds greatly improves the ability of Bayesian Network analysis to learn gene interaction networks from gene expression data. We demonstrate that the use of seeds derived from the biomedical literature or high-throughput protein-protein interaction data, or the combination, provides improvement over a standard Bayesian Network analysis, allowing networks involving dynamic processes to be deduced from the static snapshots of biological systems that represent the most common source of microarray data. Software implementing these methods has been included in the widely used TM4 microarray analysis package.
Understanding Computational Bayesian Statistics
Bolstad, William M
2011-01-01
A hands-on introduction to computational statistics from a Bayesian point of view Providing a solid grounding in statistics while uniquely covering the topics from a Bayesian perspective, Understanding Computational Bayesian Statistics successfully guides readers through this new, cutting-edge approach. With its hands-on treatment of the topic, the book shows how samples can be drawn from the posterior distribution when the formula giving its shape is all that is known, and how Bayesian inferences can be based on these samples from the posterior. These ideas are illustrated on common statistic
Bayesian statistics an introduction
Lee, Peter M
2012-01-01
Bayesian Statistics is the school of thought that combines prior beliefs with the likelihood of a hypothesis to arrive at posterior beliefs. The first edition of Peter Lee’s book appeared in 1989, but the subject has moved ever onwards, with increasing emphasis on Monte Carlo based techniques. This new fourth edition looks at recent techniques such as variational methods, Bayesian importance sampling, approximate Bayesian computation and Reversible Jump Markov Chain Monte Carlo (RJMCMC), providing a concise account of the way in which the Bayesian approach to statistics develops as wel
Bayesian estimation and tracking a practical guide
Haug, Anton J
2012-01-01
A practical approach to estimating and tracking dynamic systems in real-worl applications Much of the literature on performing estimation for non-Gaussian systems is short on practical methodology, while Gaussian methods often lack a cohesive derivation. Bayesian Estimation and Tracking addresses the gap in the field on both accounts, providing readers with a comprehensive overview of methods for estimating both linear and nonlinear dynamic systems driven by Gaussian and non-Gaussian noices. Featuring a unified approach to Bayesian estimation and tracking, the book emphasizes the derivation
Energy Technology Data Exchange (ETDEWEB)
Chikkagoudar, Satish; Chatterjee, Samrat; Thomas, Dennis G.; Carroll, Thomas E.; Muller, George
2017-04-21
The absence of a robust and unified theory of cyber dynamics presents challenges and opportunities for using machine learning based data-driven approaches to further the understanding of the behavior of such complex systems. Analysts can also use machine learning approaches to gain operational insights. In order to be operationally beneficial, cybersecurity machine learning based models need to have the ability to: (1) represent a real-world system, (2) infer system properties, and (3) learn and adapt based on expert knowledge and observations. Probabilistic models and Probabilistic graphical models provide these necessary properties and are further explored in this chapter. Bayesian Networks and Hidden Markov Models are introduced as an example of a widely used data driven classification/modeling strategy.
Qudrat-Ullah, Hassan
2010-01-01
The use of simulations in general and of system dynamics simulation based interactive learning environments (SDILEs) in particular is well recognized as an effective way of improving users' decision making and learning in complex, dynamic tasks. However, the effectiveness of SDILEs in classrooms has rarely been evaluated. This article describes…
Dynamic Training Elements in a Circuit Theory Course to Implement a Self-Directed Learning Process
Krouk, B. I.; Zhuravleva, O. B.
2009-01-01
This paper reports on the implementation of a self-directed learning process in a circuit theory course, incorporating dynamic training elements which were designed on the basis of a cybernetic model of cognitive process management. These elements are centrally linked in a dynamic learning frame, created on the monitor screen, which displays the…
Probabilistic learning of nonlinear dynamical systems using sequential Monte Carlo
Schön, Thomas B.; Svensson, Andreas; Murray, Lawrence; Lindsten, Fredrik
2018-05-01
Probabilistic modeling provides the capability to represent and manipulate uncertainty in data, models, predictions and decisions. We are concerned with the problem of learning probabilistic models of dynamical systems from measured data. Specifically, we consider learning of probabilistic nonlinear state-space models. There is no closed-form solution available for this problem, implying that we are forced to use approximations. In this tutorial we will provide a self-contained introduction to one of the state-of-the-art methods-the particle Metropolis-Hastings algorithm-which has proven to offer a practical approximation. This is a Monte Carlo based method, where the particle filter is used to guide a Markov chain Monte Carlo method through the parameter space. One of the key merits of the particle Metropolis-Hastings algorithm is that it is guaranteed to converge to the "true solution" under mild assumptions, despite being based on a particle filter with only a finite number of particles. We will also provide a motivating numerical example illustrating the method using a modeling language tailored for sequential Monte Carlo methods. The intention of modeling languages of this kind is to open up the power of sophisticated Monte Carlo methods-including particle Metropolis-Hastings-to a large group of users without requiring them to know all the underlying mathematical details.
Directory of Open Access Journals (Sweden)
Abdul Majid
2011-10-01
Full Text Available Organizational and individual learning are two different concepts in contemporaryorganizational theory. Organizational learning is a difficult concept which needs to be furtherelucidated for organizational practitioner at actual work setting; especially in the developingcountries like Pakistan. This paper reviews the literature on organizational learning intransformational change, and the comparative learning processes in the developed anddeveloping economies. Furthermore, we are dealing here with the proposed learning cycle instrategic change process with special reference to the developing countries.Keywords: Learning cycle, Transformational change, Innovation, Learning Dynamics
Yuan, Ying; MacKinnon, David P.
2009-01-01
In this article, we propose Bayesian analysis of mediation effects. Compared with conventional frequentist mediation analysis, the Bayesian approach has several advantages. First, it allows researchers to incorporate prior information into the mediation analysis, thus potentially improving the efficiency of estimates. Second, under the Bayesian…
Kleibergen, F.R.; Kleijn, R.; Paap, R.
2000-01-01
We propose a novel Bayesian test under a (noninformative) Jeffreys'priorspecification. We check whether the fixed scalar value of the so-calledBayesian Score Statistic (BSS) under the null hypothesis is aplausiblerealization from its known and standardized distribution under thealternative. Unlike
Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network.
Gilra, Aditya; Gerstner, Wulfram
2017-11-27
The brain needs to predict how the body reacts to motor commands, but how a network of spiking neurons can learn non-linear body dynamics using local, online and stable learning rules is unclear. Here, we present a supervised learning scheme for the feedforward and recurrent connections in a network of heterogeneous spiking neurons. The error in the output is fed back through fixed random connections with a negative gain, causing the network to follow the desired dynamics. The rule for Feedback-based Online Local Learning Of Weights (FOLLOW) is local in the sense that weight changes depend on the presynaptic activity and the error signal projected onto the postsynaptic neuron. We provide examples of learning linear, non-linear and chaotic dynamics, as well as the dynamics of a two-link arm. Under reasonable approximations, we show, using the Lyapunov method, that FOLLOW learning is uniformly stable, with the error going to zero asymptotically.
Self-expressive Dictionary Learning for Dynamic 3D Reconstruction.
Zheng, Enliang; Ji, Dinghuang; Dunn, Enrique; Frahm, Jan-Michael
2017-08-22
We target the problem of sparse 3D reconstruction of dynamic objects observed by multiple unsynchronized video cameras with unknown temporal overlap. To this end, we develop a framework to recover the unknown structure without sequencing information across video sequences. Our proposed compressed sensing framework poses the estimation of 3D structure as the problem of dictionary learning, where the dictionary is defined as an aggregation of the temporally varying 3D structures. Given the smooth motion of dynamic objects, we observe any element in the dictionary can be well approximated by a sparse linear combination of other elements in the same dictionary (i.e. self-expression). Our formulation optimizes a biconvex cost function that leverages a compressed sensing formulation and enforces both structural dependency coherence across video streams, as well as motion smoothness across estimates from common video sources. We further analyze the reconstructability of our approach under different capture scenarios, and its comparison and relation to existing methods. Experimental results on large amounts of synthetic data as well as real imagery demonstrate the effectiveness of our approach.
A model of dynamic learning creativity, innovation and entrepreneurship
Directory of Open Access Journals (Sweden)
Franc Vidic
2012-03-01
Full Text Available Recession, instability, unemployment and the rapid pace of change produce uncertainty, but also bring opportuni- ties for enterprising and creative activities. It is important to encourage creativity, a sense of awareness of one’s own strength and value, initiative and responsibility, to develop entrepreneurial competences and creative and critical thinking: it is necessary to strengthen the ability to recognize and track opportunities in order to develop new ideas, create new ventures and acquire the necessary resources. In view of the dynamic nature of environment, it is necessary to create several differently oriented programmes at various levels. How can such an educational challenge be tackled? We have developed a dynamic learning model for creativity, innovation and entrepreneurship. The model encourages strengthening of entrepreneurial skills in individuals, groups and in the social environment to convert ideas into action. Education should encourage creativity, innovation, risk taking, planning and management. These skills can be used in a wide range of activities - at home, at work and in the society. Students should be able to identify problems and find solutions for them.
A Dynamic Neighborhood Learning-Based Gravitational Search Algorithm.
Zhang, Aizhu; Sun, Genyun; Ren, Jinchang; Li, Xiaodong; Wang, Zhenjie; Jia, Xiuping
2018-01-01
Balancing exploration and exploitation according to evolutionary states is crucial to meta-heuristic search (M-HS) algorithms. Owing to its simplicity in theory and effectiveness in global optimization, gravitational search algorithm (GSA) has attracted increasing attention in recent years. However, the tradeoff between exploration and exploitation in GSA is achieved mainly by adjusting the size of an archive, named , which stores those superior agents after fitness sorting in each iteration. Since the global property of remains unchanged in the whole evolutionary process, GSA emphasizes exploitation over exploration and suffers from rapid loss of diversity and premature convergence. To address these problems, in this paper, we propose a dynamic neighborhood learning (DNL) strategy to replace the model and thereby present a DNL-based GSA (DNLGSA). The method incorporates the local and global neighborhood topologies for enhancing the exploration and obtaining adaptive balance between exploration and exploitation. The local neighborhoods are dynamically formed based on evolutionary states. To delineate the evolutionary states, two convergence criteria named limit value and population diversity, are introduced. Moreover, a mutation operator is designed for escaping from the local optima on the basis of evolutionary states. The proposed algorithm was evaluated on 27 benchmark problems with different characteristic and various difficulties. The results reveal that DNLGSA exhibits competitive performances when compared with a variety of state-of-the-art M-HS algorithms. Moreover, the incorporation of local neighborhood topology reduces the numbers of calculations of gravitational force and thus alleviates the high computational cost of GSA.
von der Linden, Wolfgang; Dose, Volker; von Toussaint, Udo
2014-06-01
Preface; Part I. Introduction: 1. The meaning of probability; 2. Basic definitions; 3. Bayesian inference; 4. Combinatrics; 5. Random walks; 6. Limit theorems; 7. Continuous distributions; 8. The central limit theorem; 9. Poisson processes and waiting times; Part II. Assigning Probabilities: 10. Transformation invariance; 11. Maximum entropy; 12. Qualified maximum entropy; 13. Global smoothness; Part III. Parameter Estimation: 14. Bayesian parameter estimation; 15. Frequentist parameter estimation; 16. The Cramer-Rao inequality; Part IV. Testing Hypotheses: 17. The Bayesian way; 18. The frequentist way; 19. Sampling distributions; 20. Bayesian vs frequentist hypothesis tests; Part V. Real World Applications: 21. Regression; 22. Inconsistent data; 23. Unrecognized signal contributions; 24. Change point problems; 25. Function estimation; 26. Integral equations; 27. Model selection; 28. Bayesian experimental design; Part VI. Probabilistic Numerical Techniques: 29. Numerical integration; 30. Monte Carlo methods; 31. Nested sampling; Appendixes; References; Index.
Learning nitrogen-vacancy electron spin dynamics on a silicon quantum photonic simulator
Wang, J.; Paesani, S.; Santagati, R.; Knauer, S.; Gentile, A. A.; Wiebe, N.; Petruzzella, M.; Laing, A.; Rarity, J. G.; O'Brien, J. L.; Thompson, M. G.
2017-01-01
We present the experimental demonstration of quantum Hamiltonian learning. Using an integrated silicon-photonics quantum simulator with the classical machine learning technique, we successfully learn the Hamiltonian dynamics of a diamond nitrogen-vacancy center's electron ground-state spin.
Steenbergen, B.; van der Kamp, J.; Verneau, M.M.N.; Jongbloed-Pereboom, M.; Masters, R.S.
2010-01-01
Purpose. Motor skills can be learned in an explicit or an implicit manner. Explicit learning places high demands on working memory capacity, but engagement of working memory is largely circumvented when skills are learned implicitly. We propose that individuals with impaired movement dynamics may
Steenbergen, B.; Kamp, J. van der; Verneau, M.; Jongbloed-Pereboom, M.; Masters, R.S.
2010-01-01
PURPOSE: Motor skills can be learned in an explicit or an implicit manner. Explicit learning places high demands on working memory capacity, but engagement of working memory is largely circumvented when skills are learned implicitly. We propose that individuals with impaired movement dynamics may
Steenbergen, B.; Kamp, J. van der; Verneau, M.; Jongbloed-Pereboom, M.; Masters, R.S.W.
2010-01-01
Purpose - Motor skills can be learned in an explicit or an implicit manner. Explicit learning places high demands on working memory capacity, but engagement of working memory is largely circumvented when skills are learned implicitly. We propose that individuals with impaired movement dynamics may
Deep Learning and Bayesian Methods
Prosper Harrison B.
2017-01-01
A revolution is underway in which deep neural networks are routinely used to solve diffcult problems such as face recognition and natural language understanding. Particle physicists have taken notice and have started to deploy these methods, achieving results that suggest a potentially significant shift in how data might be analyzed in the not too distant future. We discuss a few recent developments in the application of deep neural networks and then indulge in speculation about how such meth...
Bayesian phylogeography finds its roots.
Directory of Open Access Journals (Sweden)
Philippe Lemey
2009-09-01
Full Text Available As a key factor in endemic and epidemic dynamics, the geographical distribution of viruses has been frequently interpreted in the light of their genetic histories. Unfortunately, inference of historical dispersal or migration patterns of viruses has mainly been restricted to model-free heuristic approaches that provide little insight into the temporal setting of the spatial dynamics. The introduction of probabilistic models of evolution, however, offers unique opportunities to engage in this statistical endeavor. Here we introduce a Bayesian framework for inference, visualization and hypothesis testing of phylogeographic history. By implementing character mapping in a Bayesian software that samples time-scaled phylogenies, we enable the reconstruction of timed viral dispersal patterns while accommodating phylogenetic uncertainty. Standard Markov model inference is extended with a stochastic search variable selection procedure that identifies the parsimonious descriptions of the diffusion process. In addition, we propose priors that can incorporate geographical sampling distributions or characterize alternative hypotheses about the spatial dynamics. To visualize the spatial and temporal information, we summarize inferences using virtual globe software. We describe how Bayesian phylogeography compares with previous parsimony analysis in the investigation of the influenza A H5N1 origin and H5N1 epidemiological linkage among sampling localities. Analysis of rabies in West African dog populations reveals how virus diffusion may enable endemic maintenance through continuous epidemic cycles. From these analyses, we conclude that our phylogeographic framework will make an important asset in molecular epidemiology that can be easily generalized to infer biogeogeography from genetic data for many organisms.
Davis, Dannielle Joy; Major, Amanda; Cook, Debra; Bell, Janel
2015-01-01
Service learning strengthens all involved: Students, faculty members, the community, and higher education institutions. Benefits of service learning for students include gaining real world experiences, personal and transformative outcomes (Conway, Amel, & Gerwien’s, 2009), as well as higher order thinking from reflection on the experience (Molee, Henry, Sessa, & McKinney-Prupis, 2010). To understand the dynamics of service learning upon students' learning and transformati...
Encoding dependence in Bayesian causal networks
Bayesian networks (BNs) represent complex, uncertain spatio-temporal dynamics by propagation of conditional probabilities between identifiable states with a testable causal interaction model. Typically, they assume random variables are discrete in time and space with a static network structure that ...
Memory Transformation Enhances Reinforcement Learning in Dynamic Environments.
Santoro, Adam; Frankland, Paul W; Richards, Blake A
2016-11-30
Over the course of systems consolidation, there is a switch from a reliance on detailed episodic memories to generalized schematic memories. This switch is sometimes referred to as "memory transformation." Here we demonstrate a previously unappreciated benefit of memory transformation, namely, its ability to enhance reinforcement learning in a dynamic environment. We developed a neural network that is trained to find rewards in a foraging task where reward locations are continuously changing. The network can use memories for specific locations (episodic memories) and statistical patterns of locations (schematic memories) to guide its search. We find that switching from an episodic to a schematic strategy over time leads to enhanced performance due to the tendency for the reward location to be highly correlated with itself in the short-term, but regress to a stable distribution in the long-term. We also show that the statistics of the environment determine the optimal utilization of both types of memory. Our work recasts the theoretical question of why memory transformation occurs, shifting the focus from the avoidance of memory interference toward the enhancement of reinforcement learning across multiple timescales. As time passes, memories transform from a highly detailed state to a more gist-like state, in a process called "memory transformation." Theories of memory transformation speak to its advantages in terms of reducing memory interference, increasing memory robustness, and building models of the environment. However, the role of memory transformation from the perspective of an agent that continuously acts and receives reward in its environment is not well explored. In this work, we demonstrate a view of memory transformation that defines it as a way of optimizing behavior across multiple timescales. Copyright © 2016 the authors 0270-6474/16/3612228-15$15.00/0.
Approach to Dynamic Assembling of Individualized Learning Paths
Lubchak, Vladimir; Kupenko, Olena; Kuzikov, Borys
2012-01-01
E-learning students are generally heterogeneous and have different capabilities knowledge base and needs. The aim of the Sumy State University (SSU) e-learning system project is to cater to these individual needs by assembling individual learning path. This paper shows current situation with e-learning in Ukraine, state-of-art of development of…
Flexible Heuristic Dynamic Programming for Reinforcement Learning in Quadrotors
Helmer, Alexander; de Visser, C.C.; van Kampen, E.
2018-01-01
Reinforcement learning is a paradigm for learning decision-making tasks from interaction with the environment. Function approximators solve a part of the curse of dimensionality when learning in high-dimensional state and/or action spaces. It can be a time-consuming process to learn a good policy in
Albert, Jim
2009-01-01
There has been a dramatic growth in the development and application of Bayesian inferential methods. Some of this growth is due to the availability of powerful simulation-based algorithms to summarize posterior distributions. There has been also a growing interest in the use of the system R for statistical analyses. R's open source nature, free availability, and large number of contributor packages have made R the software of choice for many statisticians in education and industry. Bayesian Computation with R introduces Bayesian modeling by the use of computation using the R language. The earl
Path to Stochastic Stability: Comparative Analysis of Stochastic Learning Dynamics in Games
Jaleel, Hassan
2018-04-08
Stochastic stability is a popular solution concept for stochastic learning dynamics in games. However, a critical limitation of this solution concept is its inability to distinguish between different learning rules that lead to the same steady-state behavior. We address this limitation for the first time and develop a framework for the comparative analysis of stochastic learning dynamics with different update rules but same steady-state behavior. We present the framework in the context of two learning dynamics: Log-Linear Learning (LLL) and Metropolis Learning (ML). Although both of these dynamics have the same stochastically stable states, LLL and ML correspond to different behavioral models for decision making. Moreover, we demonstrate through an example setup of sensor coverage game that for each of these dynamics, the paths to stochastically stable states exhibit distinctive behaviors. Therefore, we propose multiple criteria to analyze and quantify the differences in the short and medium run behavior of stochastic learning dynamics. We derive and compare upper bounds on the expected hitting time to the set of Nash equilibria for both LLL and ML. For the medium to long-run behavior, we identify a set of tools from the theory of perturbed Markov chains that result in a hierarchical decomposition of the state space into collections of states called cycles. We compare LLL and ML based on the proposed criteria and develop invaluable insights into the comparative behavior of the two dynamics.
Bayesian data analysis for newcomers.
Kruschke, John K; Liddell, Torrin M
2018-02-01
This article explains the foundational concepts of Bayesian data analysis using virtually no mathematical notation. Bayesian ideas already match your intuitions from everyday reasoning and from traditional data analysis. Simple examples of Bayesian data analysis are presented that illustrate how the information delivered by a Bayesian analysis can be directly interpreted. Bayesian approaches to null-value assessment are discussed. The article clarifies misconceptions about Bayesian methods that newcomers might have acquired elsewhere. We discuss prior distributions and explain how they are not a liability but an important asset. We discuss the relation of Bayesian data analysis to Bayesian models of mind, and we briefly discuss what methodological problems Bayesian data analysis is not meant to solve. After you have read this article, you should have a clear sense of how Bayesian data analysis works and the sort of information it delivers, and why that information is so intuitive and useful for drawing conclusions from data.
Bayesian Inference Methods for Sparse Channel Estimation
DEFF Research Database (Denmark)
Pedersen, Niels Lovmand
2013-01-01
This thesis deals with sparse Bayesian learning (SBL) with application to radio channel estimation. As opposed to the classical approach for sparse signal representation, we focus on the problem of inferring complex signals. Our investigations within SBL constitute the basis for the development...... of Bayesian inference algorithms for sparse channel estimation. Sparse inference methods aim at finding the sparse representation of a signal given in some overcomplete dictionary of basis vectors. Within this context, one of our main contributions to the field of SBL is a hierarchical representation...... analysis of the complex prior representation, where we show that the ability to induce sparse estimates of a given prior heavily depends on the inference method used and, interestingly, whether real or complex variables are inferred. We also show that the Bayesian estimators derived from the proposed...
Bayesian methods for data analysis
Carlin, Bradley P.
2009-01-01
Approaches for statistical inference Introduction Motivating Vignettes Defining the Approaches The Bayes-Frequentist Controversy Some Basic Bayesian Models The Bayes approach Introduction Prior Distributions Bayesian Inference Hierarchical Modeling Model Assessment Nonparametric Methods Bayesian computation Introduction Asymptotic Methods Noniterative Monte Carlo Methods Markov Chain Monte Carlo Methods Model criticism and selection Bayesian Modeling Bayesian Robustness Model Assessment Bayes Factors via Marginal Density Estimation Bayes Factors
Coupled replicator equations for the dynamics of learning in multiagent systems
Sato, Yuzuru; Crutchfield, James P.
2003-01-01
Starting with a group of reinforcement-learning agents we derive coupled replicator equations that describe the dynamics of collective learning in multiagent systems. We show that, although agents model their environment in a self-interested way without sharing knowledge, a game dynamics emerges naturally through environment-mediated interactions. An application to rock-scissors-paper game interactions shows that the collective learning dynamics exhibits a diversity of competitive and cooperative behaviors. These include quasiperiodicity, stable limit cycles, intermittency, and deterministic chaos—behaviors that should be expected in heterogeneous multiagent systems described by the general replicator equations we derive.
Noncausal Bayesian Vector Autoregression
DEFF Research Database (Denmark)
Lanne, Markku; Luoto, Jani
We propose a Bayesian inferential procedure for the noncausal vector autoregressive (VAR) model that is capable of capturing nonlinearities and incorporating effects of missing variables. In particular, we devise a fast and reliable posterior simulator that yields the predictive distribution...
Statistics: a Bayesian perspective
National Research Council Canada - National Science Library
Berry, Donald A
1996-01-01
...: it is the only introductory textbook based on Bayesian ideas, it combines concepts and methods, it presents statistics as a means of integrating data into the significant process, it develops ideas...
Fox, Gerardus J.A.; van den Berg, Stéphanie Martine; Veldkamp, Bernard P.; Irwing, P.; Booth, T.; Hughes, D.
2015-01-01
In educational and psychological studies, psychometric methods are involved in the measurement of constructs, and in constructing and validating measurement instruments. Assessment results are typically used to measure student proficiency levels and test characteristics. Recently, Bayesian item
Episodic memory deficits slow down the dynamics of cognitive procedural learning in normal ageing
Beaunieux, Hélène; Hubert, Valérie; Pitel, Anne Lise; Desgranges, Béatrice; Eustache, Francis
2009-01-01
Cognitive procedural learning is characterized by three phases, each involving distinct processes. Considering the implication of the episodic memory in the first cognitive stage, the impairment of this memory system might be responsible for a slowing down of the cognitive procedural learning dynamics in the course of aging. Performances of massed cognitive procedural learning were evaluated in older and younger participants using the Tower of Toronto task. Nonverbal intelligence and psychomotor abilities were used to analyze procedural dynamics, while episodic memory and working memory were assessed to measure their respective contributions to learning strategies. This experiment showed that older participants did not spontaneously invoke episodic memory and presented a slowdown in the cognitive procedural learning associated with a late involvement of working memory. These findings suggest that the slowdown in the cognitive procedural learning may be linked with the implementation of different learning strategies less involving episodic memory in older subjects. PMID:18654928
Bayesian Networks An Introduction
Koski, Timo
2009-01-01
Bayesian Networks: An Introduction provides a self-contained introduction to the theory and applications of Bayesian networks, a topic of interest and importance for statisticians, computer scientists and those involved in modelling complex data sets. The material has been extensively tested in classroom teaching and assumes a basic knowledge of probability, statistics and mathematics. All notions are carefully explained and feature exercises throughout. Features include:.: An introduction to Dirichlet Distribution, Exponential Families and their applications.; A detailed description of learni
Ghosh, Sujit K
2010-01-01
Bayesian methods are rapidly becoming popular tools for making statistical inference in various fields of science including biology, engineering, finance, and genetics. One of the key aspects of Bayesian inferential method is its logical foundation that provides a coherent framework to utilize not only empirical but also scientific information available to a researcher. Prior knowledge arising from scientific background, expert judgment, or previously collected data is used to build a prior distribution which is then combined with current data via the likelihood function to characterize the current state of knowledge using the so-called posterior distribution. Bayesian methods allow the use of models of complex physical phenomena that were previously too difficult to estimate (e.g., using asymptotic approximations). Bayesian methods offer a means of more fully understanding issues that are central to many practical problems by allowing researchers to build integrated models based on hierarchical conditional distributions that can be estimated even with limited amounts of data. Furthermore, advances in numerical integration methods, particularly those based on Monte Carlo methods, have made it possible to compute the optimal Bayes estimators. However, there is a reasonably wide gap between the background of the empirically trained scientists and the full weight of Bayesian statistical inference. Hence, one of the goals of this chapter is to bridge the gap by offering elementary to advanced concepts that emphasize linkages between standard approaches and full probability modeling via Bayesian methods.
The Dynamics of Learning and the Emergence of Distributed Adaption
National Research Council Canada - National Science Library
Crutchfield, James P
2006-01-01
.... The second goal was to adapt this single-agent learning theory and associated learning algorithms to the distributed setting in which a population of autonomous agents communicate to achieve a desired group task...
Learning what to see in a changing world
Directory of Open Access Journals (Sweden)
Katharina eSchmack
2016-05-01
Full Text Available Visual perception is strongly shaped by expectations, but it is poorly understood how such perceptual expectations are learned in our dynamic sensory environment. Here, we applied a Bayesian framework to investigate whether perceptual expectations are continuously updated from different aspects of ongoing experience. In two experiments, human observers performed an associative learning task in which rapidly changing expectations about the appearance of ambiguous stimuli were induced. We found that perception of ambiguous stimuli was biased by both learned associations and previous perceptual outcomes. Computational modelling revealed that perception was best explained by amodel that continuously updated priors from associative learning and perceptual history and combined these priors with the current sensory information in a probabilistic manner. Our findings suggest that the construction of visual perception is a highly dynamic process that incorporates rapidly changing expectations from different sources in a manner consistent with Bayesian learning and inference.
Van Gog, Tamara; Paas, Fred; Marcus, Nadine; Ayres, Paul; Sweller, John
2009-01-01
Van Gog, T., Paas, F., Marcus, N., Ayres, P., & Sweller, J. (2009). The mirror-neuron system and observational learning: Implications for the effectiveness of dynamic visualizations. Educational Psychology Review, 21, 21-30.
A self-learning rule base for command following in dynamical systems
Tsai, Wei K.; Lee, Hon-Mun; Parlos, Alexander
1992-01-01
In this paper, a self-learning Rule Base for command following in dynamical systems is presented. The learning is accomplished though reinforcement learning using an associative memory called SAM. The main advantage of SAM is that it is a function approximator with explicit storage of training samples. A learning algorithm patterned after the dynamic programming is proposed. Two artificially created, unstable dynamical systems are used for testing, and the Rule Base was used to generate a feedback control to improve the command following ability of the otherwise uncontrolled systems. The numerical results are very encouraging. The controlled systems exhibit a more stable behavior and a better capability to follow reference commands. The rules resulting from the reinforcement learning are explicitly stored and they can be modified or augmented by human experts. Due to overlapping storage scheme of SAM, the stored rules are similar to fuzzy rules.
Study on shielded pump system failure analysis method based on Bayesian network
International Nuclear Information System (INIS)
Bao Yilan; Huang Gaofeng; Tong Lili; Cao Xuewu
2012-01-01
This paper applies Bayesian network to the system failure analysis, with an aim to improve knowledge representation of the uncertainty logic and multi-fault states in system failure analysis. A Bayesian network for shielded pump failure analysis is presented, conducting fault parameter learning, updating Bayesian network parameter based on new samples. Finally, through the Bayesian network inference, vulnerability in this system, the largest possible failure modes, and the fault probability are obtained. The powerful ability of Bayesian network to analyze system fault is illustrated by examples. (authors)
Bayesian ensemble refinement by replica simulations and reweighting
Hummer, Gerhard; Köfinger, Jürgen
2015-12-01
We describe different Bayesian ensemble refinement methods, examine their interrelation, and discuss their practical application. With ensemble refinement, the properties of dynamic and partially disordered (bio)molecular structures can be characterized by integrating a wide range of experimental data, including measurements of ensemble-averaged observables. We start from a Bayesian formulation in which the posterior is a functional that ranks different configuration space distributions. By maximizing this posterior, we derive an optimal Bayesian ensemble distribution. For discrete configurations, this optimal distribution is identical to that obtained by the maximum entropy "ensemble refinement of SAXS" (EROS) formulation. Bayesian replica ensemble refinement enhances the sampling of relevant configurations by imposing restraints on averages of observables in coupled replica molecular dynamics simulations. We show that the strength of the restraints should scale linearly with the number of replicas to ensure convergence to the optimal Bayesian result in the limit of infinitely many replicas. In the "Bayesian inference of ensembles" method, we combine the replica and EROS approaches to accelerate the convergence. An adaptive algorithm can be used to sample directly from the optimal ensemble, without replicas. We discuss the incorporation of single-molecule measurements and dynamic observables such as relaxation parameters. The theoretical analysis of different Bayesian ensemble refinement approaches provides a basis for practical applications and a starting point for further investigations.
Error modeling for surrogates of dynamical systems using machine learning
Trehan, Sumeet; Carlberg, Kevin T.; Durlofsky, Louis J.
2017-12-01
A machine-learning-based framework for modeling the error introduced by surrogate models of parameterized dynamical systems is proposed. The framework entails the use of high-dimensional regression techniques (e.g., random forests, LASSO) to map a large set of inexpensively computed `error indicators' (i.e., features) produced by the surrogate model at a given time instance to a prediction of the surrogate-model error in a quantity of interest (QoI). This eliminates the need for the user to hand-select a small number of informative features. The methodology requires a training set of parameter instances at which the time-dependent surrogate-model error is computed by simulating both the high-fidelity and surrogate models. Using these training data, the method first determines regression-model locality (via classification or clustering), and subsequently constructs a `local' regression model to predict the time-instantaneous error within each identified region of feature space. We consider two uses for the resulting error model: (1) as a correction to the surrogate-model QoI prediction at each time instance, and (2) as a way to statistically model arbitrary functions of the time-dependent surrogate-model error (e.g., time-integrated errors). We apply the proposed framework to model errors in reduced-order models of nonlinear oil--water subsurface flow simulations. The reduced-order models used in this work entail application of trajectory piecewise linearization with proper orthogonal decomposition. When the first use of the method is considered, numerical experiments demonstrate consistent improvement in accuracy in the time-instantaneous QoI prediction relative to the original surrogate model, across a large number of test cases. When the second use is considered, results show that the proposed method provides accurate statistical predictions of the time- and well-averaged errors.
Catecholaminergic Regulation of Learning Rate in a Dynamic Environment.
Directory of Open Access Journals (Sweden)
Marieke Jepma
2016-10-01
Full Text Available Adaptive behavior in a changing world requires flexibly adapting one's rate of learning to the rate of environmental change. Recent studies have examined the computational mechanisms by which various environmental factors determine the impact of new outcomes on existing beliefs (i.e., the 'learning rate'. However, the brain mechanisms, and in particular the neuromodulators, involved in this process are still largely unknown. The brain-wide neurophysiological effects of the catecholamines norepinephrine and dopamine on stimulus-evoked cortical responses suggest that the catecholamine systems are well positioned to regulate learning about environmental change, but more direct evidence for a role of this system is scant. Here, we report evidence from a study employing pharmacology, scalp electrophysiology and computational modeling (N = 32 that suggests an important role for catecholamines in learning rate regulation. We found that the P3 component of the EEG-an electrophysiological index of outcome-evoked phasic catecholamine release in the cortex-predicted learning rate, and formally mediated the effect of prediction-error magnitude on learning rate. P3 amplitude also mediated the effects of two computational variables-capturing the unexpectedness of an outcome and the uncertainty of a preexisting belief-on learning rate. Furthermore, a pharmacological manipulation of catecholamine activity affected learning rate following unanticipated task changes, in a way that depended on participants' baseline learning rate. Our findings provide converging evidence for a causal role of the human catecholamine systems in learning-rate regulation as a function of environmental change.
Catecholaminergic Regulation of Learning Rate in a Dynamic Environment.
Jepma, Marieke; Murphy, Peter R; Nassar, Matthew R; Rangel-Gomez, Mauricio; Meeter, Martijn; Nieuwenhuis, Sander
2016-10-01
Adaptive behavior in a changing world requires flexibly adapting one's rate of learning to the rate of environmental change. Recent studies have examined the computational mechanisms by which various environmental factors determine the impact of new outcomes on existing beliefs (i.e., the 'learning rate'). However, the brain mechanisms, and in particular the neuromodulators, involved in this process are still largely unknown. The brain-wide neurophysiological effects of the catecholamines norepinephrine and dopamine on stimulus-evoked cortical responses suggest that the catecholamine systems are well positioned to regulate learning about environmental change, but more direct evidence for a role of this system is scant. Here, we report evidence from a study employing pharmacology, scalp electrophysiology and computational modeling (N = 32) that suggests an important role for catecholamines in learning rate regulation. We found that the P3 component of the EEG-an electrophysiological index of outcome-evoked phasic catecholamine release in the cortex-predicted learning rate, and formally mediated the effect of prediction-error magnitude on learning rate. P3 amplitude also mediated the effects of two computational variables-capturing the unexpectedness of an outcome and the uncertainty of a preexisting belief-on learning rate. Furthermore, a pharmacological manipulation of catecholamine activity affected learning rate following unanticipated task changes, in a way that depended on participants' baseline learning rate. Our findings provide converging evidence for a causal role of the human catecholamine systems in learning-rate regulation as a function of environmental change.
An Innovative Improvement of Engineering Learning System Using Computational Fluid Dynamics Concept
Hung, T. C.; Wang, S. K.; Tai, S. W.; Hung, C. T.
2007-01-01
An innovative concept of an electronic learning system has been established in an attempt to achieve a technology that provides engineering students with an instructive and affordable framework for learning engineering-related courses. This system utilizes an existing Computational Fluid Dynamics (CFD) package, Active Server Pages programming,…
Directory of Open Access Journals (Sweden)
Erhan ÜNAL
2017-04-01
Full Text Available The purpose of this study is to design a problem based collaborative learning environment supported by dynamic web technologies and examine students’ views about this learning environment. The study was designed as a qualitative research. 36 students who took Object Oriented Programming I-II course from a public university at the department of computer programming participated in the study. During the research process, the Object Oriented Programming I-II course was designed with incorporating different dynamic web technologies (Edmodo, Google Services, and Mind42 and Nelson (1999’s collaborative problem solving method. At the end of the course, there were focus group interviews in regards to the students’ views on a learning environment supported by dynamic web technologies and collaborative problem solving method. At the end of the focus group interviews, 4 themes were obtained from the students’ views, including positive aspects of the learning environment, difficulties faced in the learning environment, advantages of the learning environment, and skills gained as a result of the project. The results suggest that problem based collaborative learning methods and dynamic web technologies can be used in learning environments in community colleges.
Learning fraction comparison by using a dynamic mathematics software - GeoGebra
Poon, Kin Keung
2018-04-01
GeoGebra is a mathematics software system that can serve as a tool for inquiry-based learning. This paper deals with the application of a fraction comparison software, which is constructed by GeoGebra, for use in a dynamic mathematics environment. The corresponding teaching and learning issues have also been discussed.
Ünal, Erhan; Çakir, Hasan
2017-01-01
The purpose of this study was to design a problem based collaborative learning environment supported by dynamic web technologies and to examine students' views about this learning environment. The study was designed as a qualitative research. Some 36 students who took an Object Oriented Programming I-II course at the department of computer…
Berney, Sandra; Bétrancourt, Mireille; Molinari, Gaëlle; Hoyek, Nady
2015-01-01
The emergence of dynamic visualizations of three-dimensional (3D) models in anatomy curricula may be an adequate solution for spatial difficulties encountered with traditional static learning, as they provide direct visualization of change throughout the viewpoints. However, little research has explored the interplay between learning material…
A Study of the Effects of Multimedia Dynamic Teaching on Cognitive Load and Learning Outcome
Zhang, Xiaozhu; Zhang, Xiurong; Yang, Xiaoming
2016-01-01
The statistics reveal that about many students have learning difficulties. For this reason, appropriate curricula and materials should be planned to match with multimedia teaching design in order to reduce students' learning frustration and obstacles caused by insufficient experiences and basic competence. Multimedia dynamic, a curriculum oriented…
Learning Fraction Comparison by Using a Dynamic Mathematics Software--GeoGebra
Poon, Kin Keung
2018-01-01
GeoGebra is a mathematics software system that can serve as a tool for inquiry-based learning. This paper deals with the application of a fraction comparison software, which is constructed by GeoGebra, for use in a dynamic mathematics environment. The corresponding teaching and learning issues have also been discussed.
Arantes do Amaral, Joao Alberto
2017-01-01
In this case study we discuss the dynamics that drive a free-of-charge project-based learning extension course. We discuss the lessons learned in the course, "Laboratory of Social Projects." The course aimed to teach project management skills to the participants. It was conducted from August to November of 2015, at Federal University of…
Lucas, Colleen; Kline, Theresa
2008-01-01
Purpose: The purpose of this study is to investigate the relationship between organizational culture, group dynamics, and organizational learning in the context of organizational change. Design/methodology/approach: A case study was used to examine cultural and group level factors that potentially influence groups' learning in the context of…
Bathellier, Brice; Tee, Sui Poh; Hrovat, Christina; Rumpel, Simon
2013-01-01
Learning speed can strongly differ across individuals. This is seen in humans and animals. Here, we measured learning speed in mice performing a discrimination task and developed a theoretical model based on the reinforcement learning framework to account for differences between individual mice. We found that, when using a multiplicative learning rule, the starting connectivity values of the model strongly determine the shape of learning curves. This is in contrast to current learning models ...
Zhang, Chengwei; Li, Xiaohong; Li, Shuxin; Feng, Zhiyong
2017-09-20
Biological environment is uncertain and its dynamic is similar to the multiagent environment, thus the research results of the multiagent system area can provide valuable insights to the understanding of biology and are of great significance for the study of biology. Learning in a multiagent environment is highly dynamic since the environment is not stationary anymore and each agent's behavior changes adaptively in response to other coexisting learners, and vice versa. The dynamics becomes more unpredictable when we move from fixed-agent interaction environments to multiagent social learning framework. Analytical understanding of the underlying dynamics is important and challenging. In this work, we present a social learning framework with homogeneous learners (e.g., Policy Hill Climbing (PHC) learners), and model the behavior of players in the social learning framework as a hybrid dynamical system. By analyzing the dynamical system, we obtain some conditions about convergence or non-convergence. We experimentally verify the predictive power of our model using a number of representative games. Experimental results confirm the theoretical analysis. Under multiagent social learning framework, we modeled the behavior of agent in biologic environment, and theoretically analyzed the dynamics of the model. We present some sufficient conditions about convergence or non-convergence and prove them theoretically. It can be used to predict the convergence of the system.
Technology in postgraduate medical education: a dynamic influence on learning?
Bullock, Alison; Webb, Katie
2015-01-01
The influence of technology in medical workplace learning is explored by focusing on three uses: m-learning (notably apps), simulation and social media. Smartphones with point-of-care tools (such as textbooks, drug guides and medical calculators) can support workplace learning and doctors’ decision-making. Simulations can help develop technical skills and team interactions, and ‘in situ’ simulations improve the match between the virtual and the real. Social media (wikis, blogs, networking, Yo...
Mind map learning for advanced engineering study: case study in system dynamics
Woradechjumroen, Denchai
2018-01-01
System Dynamics (SD) is one of the subjects that were use in learning Automatic Control Systems in dynamic and control field. Mathematical modelling and solving skills of students for engineering systems are expecting outcomes of the course which can be further used to efficiently study control systems and mechanical vibration; however, the fundamental of the SD includes strong backgrounds in Dynamics and Differential Equations, which are appropriate to the students in governmental universities that have strong skills in Mathematics and Scientifics. For private universities, students are weak in the above subjects since they obtained high vocational certificate from Technical College or Polytechnic School, which emphasize the learning contents in practice. To enhance their learning for improving their backgrounds, this paper applies mind maps based problem based learning to relate the essential relations of mathematical and physical equations. With the advantages of mind maps, each student is assigned to design individual mind maps for self-leaning development after they attend the class and learn overall picture of each chapter from the class instructor. Four problems based mind maps learning are assigned to each student. Each assignment is evaluated via mid-term and final examinations, which are issued in terms of learning concepts and applications. In the method testing, thirty students are tested and evaluated via student learning backgrounds in the past. The result shows that well-design mind maps can improve learning performance based on outcome evaluation. Especially, mind maps can reduce time-consuming and reviewing for Mathematics and Physics in SD significantly.
Reinforcement learning in complementarity game and population dynamics.
Jost, Jürgen; Li, Wei
2014-02-01
We systematically test and compare different reinforcement learning schemes in a complementarity game [J. Jost and W. Li, Physica A 345, 245 (2005)] played between members of two populations. More precisely, we study the Roth-Erev, Bush-Mosteller, and SoftMax reinforcement learning schemes. A modified version of Roth-Erev with a power exponent of 1.5, as opposed to 1 in the standard version, performs best. We also compare these reinforcement learning strategies with evolutionary schemes. This gives insight into aspects like the issue of quick adaptation as opposed to systematic exploration or the role of learning rates.
Bayesian networks with examples in R
Scutari, Marco
2014-01-01
Introduction. The Discrete Case: Multinomial Bayesian Networks. The Continuous Case: Gaussian Bayesian Networks. More Complex Cases. Theory and Algorithms for Bayesian Networks. Real-World Applications of Bayesian Networks. Appendices. Bibliography.
Haptic Paddle Enhancements and a Formal Assessment of Student Learning in System Dynamics
Gorlewicz, Jenna L.; Kratchman, Louis B.; Webster, Robert J., III
2014-01-01
The haptic paddle is a force-feedback joystick used at several universities in teaching System Dynamics, a core mechanical engineering undergraduate course where students learn to model dynamic systems in several domains. A second goal of the haptic paddle is to increase the accessibility of robotics and haptics by providing a low-cost device for…
Learning dynamics and the support for economic reforms: why good news can be bad
van Wijnbergen, S.; Willems, T.
2012-01-01
Support for economic reforms has often shown puzzling dynamics: there are many examples of reforms that started off successfully but nevertheless lost public support, and vice versa. We show that learning dynamics can rationalize this apparent paradox, the reason being that the process of revealing
Bayesian methods in reliability
Sander, P.; Badoux, R.
1991-11-01
The present proceedings from a course on Bayesian methods in reliability encompasses Bayesian statistical methods and their computational implementation, models for analyzing censored data from nonrepairable systems, the traits of repairable systems and growth models, the use of expert judgment, and a review of the problem of forecasting software reliability. Specific issues addressed include the use of Bayesian methods to estimate the leak rate of a gas pipeline, approximate analyses under great prior uncertainty, reliability estimation techniques, and a nonhomogeneous Poisson process. Also addressed are the calibration sets and seed variables of expert judgment systems for risk assessment, experimental illustrations of the use of expert judgment for reliability testing, and analyses of the predictive quality of software-reliability growth models such as the Weibull order statistics.
Ubiquitous English Learning System with Dynamic Personalized Guidance of Learning Portfolio
Wu, Ting-Ting; Sung, Tien-Wen; Huang, Yueh-Min; Yang, Chu-Sing; Yang, Jin-Tan
2011-01-01
Situated learning has been recognized as an effective approach in enhancing learning impressions and experiences for students. Can we take advantage of situated learning in helping students who are not English native speakers to read English articles more effective? Can the effectiveness of situated learning be further promoted by individual…
Contrasting dynamics of organizational learning : a process theory perspective
Berends, J.J.; Lammers, I.S.
2006-01-01
In this paper we analyze the process characteristics of organizational learning. A wide variety of process models of organizational learning have been proposed in the literature, but these models have not been systematically investigated. In this paper we use Van de Ven and Poole's (1995) taxonomy
Remote Histology Learning from Static versus Dynamic Microscopic Images
Mione, Sylvia; Valcke, Martin; Cornelissen, Maria
2016-01-01
Histology is the study of microscopic structures in normal tissue sections. Curriculum redesign in medicine has led to a decrease in the use of optical microscopes during practical classes. Other imaging solutions have been implemented to facilitate remote learning. With advancements in imaging technologies, learning material can now be digitized.…
Catecholaminergic Regulation of Learning Rate in a Dynamic Environment
Jepma, Marieke; Murphy, Peter R.; Nassar, Matthew R.; Rangel-Gomez, Mauricio; Meeter, Martijn; Nieuwenhuis, Sander
2016-01-01
Adaptive behavior in a changing world requires flexibly adapting one’s rate of learning to the rate of environmental change. Recent studies have examined the computational mechanisms by which various environmental factors determine the impact of new outcomes on existing beliefs (i.e., the ‘learning
Organizing for Spaces and Dynamics of Multipolar Learning in Multinational Corporations
DEFF Research Database (Denmark)
Hull Kristensen, Peer; Lotz, Maja
Limited research has been conducted on how MNCs organize conditions and spaces for recursive learning to facilitate the practice of innovation across dispersed units as well as how organizational members at all levels may become involved in innovations through the engagement in ongoing multipolar...... learning dynamics. Based on longitudinal case studies in two MNCs this paper contributes with insights into how spaces and dynamics of multipolar learning are organized and governed across dispersed MNC units at the micro level of everyday work practices. The paper shows that it is possible to organize...... spaces and dynamics that can organize recursiveness and continuity in multipolar learning by way of experimentation with new coordination components and governance architectures. Against the previous literature, however, it becomes evident that these are not the outcome of spontaneous interactions...
Learning by stimulation avoidance: A principle to control spiking neural networks dynamics.
Sinapayen, Lana; Masumori, Atsushi; Ikegami, Takashi
2017-01-01
Learning based on networks of real neurons, and learning based on biologically inspired models of neural networks, have yet to find general learning rules leading to widespread applications. In this paper, we argue for the existence of a principle allowing to steer the dynamics of a biologically inspired neural network. Using carefully timed external stimulation, the network can be driven towards a desired dynamical state. We term this principle "Learning by Stimulation Avoidance" (LSA). We demonstrate through simulation that the minimal sufficient conditions leading to LSA in artificial networks are also sufficient to reproduce learning results similar to those obtained in biological neurons by Shahaf and Marom, and in addition explains synaptic pruning. We examined the underlying mechanism by simulating a small network of 3 neurons, then scaled it up to a hundred neurons. We show that LSA has a higher explanatory power than existing hypotheses about the response of biological neural networks to external simulation, and can be used as a learning rule for an embodied application: learning of wall avoidance by a simulated robot. In other works, reinforcement learning with spiking networks can be obtained through global reward signals akin simulating the dopamine system; we believe that this is the first project demonstrating sensory-motor learning with random spiking networks through Hebbian learning relying on environmental conditions without a separate reward system.
Bayesian Correlation Analysis for Sequence Count Data.
Directory of Open Access Journals (Sweden)
Daniel Sánchez-Taltavull
Full Text Available Evaluating the similarity of different measured variables is a fundamental task of statistics, and a key part of many bioinformatics algorithms. Here we propose a Bayesian scheme for estimating the correlation between different entities' measurements based on high-throughput sequencing data. These entities could be different genes or miRNAs whose expression is measured by RNA-seq, different transcription factors or histone marks whose expression is measured by ChIP-seq, or even combinations of different types of entities. Our Bayesian formulation accounts for both measured signal levels and uncertainty in those levels, due to varying sequencing depth in different experiments and to varying absolute levels of individual entities, both of which affect the precision of the measurements. In comparison with a traditional Pearson correlation analysis, we show that our Bayesian correlation analysis retains high correlations when measurement confidence is high, but suppresses correlations when measurement confidence is low-especially for entities with low signal levels. In addition, we consider the influence of priors on the Bayesian correlation estimate. Perhaps surprisingly, we show that naive, uniform priors on entities' signal levels can lead to highly biased correlation estimates, particularly when different experiments have widely varying sequencing depths. However, we propose two alternative priors that provably mitigate this problem. We also prove that, like traditional Pearson correlation, our Bayesian correlation calculation constitutes a kernel in the machine learning sense, and thus can be used as a similarity measure in any kernel-based machine learning algorithm. We demonstrate our approach on two RNA-seq datasets and one miRNA-seq dataset.
Virtual Vector Machine for Bayesian Online Classification
Minka, Thomas P.; Xiang, Rongjing; Yuan; Qi
2012-01-01
In a typical online learning scenario, a learner is required to process a large data stream using a small memory buffer. Such a requirement is usually in conflict with a learner's primary pursuit of prediction accuracy. To address this dilemma, we introduce a novel Bayesian online classi cation algorithm, called the Virtual Vector Machine. The virtual vector machine allows you to smoothly trade-off prediction accuracy with memory size. The virtual vector machine summarizes the information con...
A Bayesian Reflection on Surfaces
Directory of Open Access Journals (Sweden)
David R. Wolf
1999-10-01
Full Text Available Abstract: The topic of this paper is a novel Bayesian continuous-basis field representation and inference framework. Within this paper several problems are solved: The maximally informative inference of continuous-basis fields, that is where the basis for the field is itself a continuous object and not representable in a finite manner; the tradeoff between accuracy of representation in terms of information learned, and memory or storage capacity in bits; the approximation of probability distributions so that a maximal amount of information about the object being inferred is preserved; an information theoretic justification for multigrid methodology. The maximally informative field inference framework is described in full generality and denoted the Generalized Kalman Filter. The Generalized Kalman Filter allows the update of field knowledge from previous knowledge at any scale, and new data, to new knowledge at any other scale. An application example instance, the inference of continuous surfaces from measurements (for example, camera image data, is presented.
On Bayesian System Reliability Analysis
Energy Technology Data Exchange (ETDEWEB)
Soerensen Ringi, M
1995-05-01
The view taken in this thesis is that reliability, the probability that a system will perform a required function for a stated period of time, depends on a person`s state of knowledge. Reliability changes as this state of knowledge changes, i.e. when new relevant information becomes available. Most existing models for system reliability prediction are developed in a classical framework of probability theory and they overlook some information that is always present. Probability is just an analytical tool to handle uncertainty, based on judgement and subjective opinions. It is argued that the Bayesian approach gives a much more comprehensive understanding of the foundations of probability than the so called frequentistic school. A new model for system reliability prediction is given in two papers. The model encloses the fact that component failures are dependent because of a shared operational environment. The suggested model also naturally permits learning from failure data of similar components in non identical environments. 85 refs.
On Bayesian System Reliability Analysis
International Nuclear Information System (INIS)
Soerensen Ringi, M.
1995-01-01
The view taken in this thesis is that reliability, the probability that a system will perform a required function for a stated period of time, depends on a person's state of knowledge. Reliability changes as this state of knowledge changes, i.e. when new relevant information becomes available. Most existing models for system reliability prediction are developed in a classical framework of probability theory and they overlook some information that is always present. Probability is just an analytical tool to handle uncertainty, based on judgement and subjective opinions. It is argued that the Bayesian approach gives a much more comprehensive understanding of the foundations of probability than the so called frequentistic school. A new model for system reliability prediction is given in two papers. The model encloses the fact that component failures are dependent because of a shared operational environment. The suggested model also naturally permits learning from failure data of similar components in non identical environments. 85 refs
Technology in postgraduate medical education: a dynamic influence on learning?
Bullock, Alison; Webb, Katie
2015-11-01
The influence of technology in medical workplace learning is explored by focusing on three uses: m-learning (notably apps), simulation and social media. Smartphones with point-of-care tools (such as textbooks, drug guides and medical calculators) can support workplace learning and doctors' decision-making. Simulations can help develop technical skills and team interactions, and 'in situ' simulations improve the match between the virtual and the real. Social media (wikis, blogs, networking, YouTube) heralds a more participatory and collaborative approach to knowledge development. These uses of technology are related to Kolb's learning cycle and Eraut's intentions of informal learning. Contentions and controversies with these technologies exist. There is a problem with the terminology commonly adopted to describe the use of technology to enhance learning. Using learning technology in the workplace changes the interaction with others and raises issues of professionalism and etiquette. Lack of regulation makes assessment of app quality a challenge. Distraction and dependency are charges levelled at smartphone use in the workplace and these need further research. Unless addressed, these and other challenges will impede the benefits that technology may bring to postgraduate medical education. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/
Interaction learning for dynamic movement primitives used in cooperative robotic tasks
DEFF Research Database (Denmark)
Kulvicius, Tomas; Biehl, Martin; Aein, Mohamad Javad
2013-01-01
Abstract Since several years dynamic movement primitives (DMPs) are more and more getting into the center of interest for flexible movement control in robotics. In this study we introduce sensory feedback together with a predictive learning mechanism which allows tightly coupled dual-agent systems...... to learn an adaptive, sensor-driven interaction based on DMPs. The coupled conventional (no-sensors, no learning) DMP-system automatically equilibrates and can still be solved analytically allowing us to derive conditions for stability. When adding adaptive sensor control we can show that both agents learn...
Understanding the Dynamics of Learning across social worlds
DEFF Research Database (Denmark)
Mengiste, Shegaw Anagaw; Aanestad, Margunn
2013-01-01
participation, politics and learning in IS implementation and use. We consider learning to be an integral part of the social practice, and it occurs mainly through encounters and negotiations between actors from different social worlds who might have competing interests and values. The paper also analysed how......This paper adopts a novel learning perspective on information systems development. Building on the works of Anselm Strauss we conceptualize development processes as “negotiated orders” where members from different “social worlds” encounter and negotiate differences and tensions. We argue...
Heuristics as Bayesian inference under extreme priors.
Parpart, Paula; Jones, Matt; Love, Bradley C
2018-05-01
Simple heuristics are often regarded as tractable decision strategies because they ignore a great deal of information in the input data. One puzzle is why heuristics can outperform full-information models, such as linear regression, which make full use of the available information. These "less-is-more" effects, in which a relatively simpler model outperforms a more complex model, are prevalent throughout cognitive science, and are frequently argued to demonstrate an inherent advantage of simplifying computation or ignoring information. In contrast, we show at the computational level (where algorithmic restrictions are set aside) that it is never optimal to discard information. Through a formal Bayesian analysis, we prove that popular heuristics, such as tallying and take-the-best, are formally equivalent to Bayesian inference under the limit of infinitely strong priors. Varying the strength of the prior yields a continuum of Bayesian models with the heuristics at one end and ordinary regression at the other. Critically, intermediate models perform better across all our simulations, suggesting that down-weighting information with the appropriate prior is preferable to entirely ignoring it. Rather than because of their simplicity, our analyses suggest heuristics perform well because they implement strong priors that approximate the actual structure of the environment. We end by considering how new heuristics could be derived by infinitely strengthening the priors of other Bayesian models. These formal results have implications for work in psychology, machine learning and economics. Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.
Understanding Digital Learning from the Perspective of Systems Dynamics
Kok, Ayse
2009-01-01
The System Dynamics approach can be seen as a new way of understanding dynamical phenonema (natural, physical, biological, etc.) that occur in our daily lives taking into consideration not only single pairs of cause-effect variables, but the functioning of the system as a whole. This approach also provides the students with a new understanding in…
Motivational Dynamics in Language Learning: Change, Stability, and Context
Waninge, Freerkien; Dörnyei, Zoltán; De Bot, Kees
2014-01-01
Motivation as a variable in L2 development is no longer seen as the stable individual difference factor it was once believed to be: Influenced by process-oriented models and principles, and especially by the growing understanding of how complex dynamic systems work, researchers have been focusing increasingly on the dynamic and changeable nature…
Bayesian methods for hackers probabilistic programming and Bayesian inference
Davidson-Pilon, Cameron
2016-01-01
Bayesian methods of inference are deeply natural and extremely powerful. However, most discussions of Bayesian inference rely on intensely complex mathematical analyses and artificial examples, making it inaccessible to anyone without a strong mathematical background. Now, though, Cameron Davidson-Pilon introduces Bayesian inference from a computational perspective, bridging theory to practice–freeing you to get results using computing power. Bayesian Methods for Hackers illuminates Bayesian inference through probabilistic programming with the powerful PyMC language and the closely related Python tools NumPy, SciPy, and Matplotlib. Using this approach, you can reach effective solutions in small increments, without extensive mathematical intervention. Davidson-Pilon begins by introducing the concepts underlying Bayesian inference, comparing it with other techniques and guiding you through building and training your first Bayesian model. Next, he introduces PyMC through a series of detailed examples a...
Modelling dependable systems using hybrid Bayesian networks
International Nuclear Information System (INIS)
Neil, Martin; Tailor, Manesh; Marquez, David; Fenton, Norman; Hearty, Peter
2008-01-01
A hybrid Bayesian network (BN) is one that incorporates both discrete and continuous nodes. In our extensive applications of BNs for system dependability assessment, the models are invariably hybrid and the need for efficient and accurate computation is paramount. We apply a new iterative algorithm that efficiently combines dynamic discretisation with robust propagation algorithms on junction tree structures to perform inference in hybrid BNs. We illustrate its use in the field of dependability with two example of reliability estimation. Firstly we estimate the reliability of a simple single system and next we implement a hierarchical Bayesian model. In the hierarchical model we compute the reliability of two unknown subsystems from data collected on historically similar subsystems and then input the result into a reliability block model to compute system level reliability. We conclude that dynamic discretisation can be used as an alternative to analytical or Monte Carlo methods with high precision and can be applied to a wide range of dependability problems
Incremental Learning for Place Recognition in Dynamic Environments
Luo, Jie; Pronobis, Andrzej; Caputo, Barbara; Jensfelt, Patric
2007-01-01
This paper proposes a discriminative approach to template-based Vision-based place recognition is a desirable feature for an autonomous mobile system. In order to work in realistic scenarios, visual recognition algorithms should be adaptive, i.e. should be able to learn from experience and adapt continuously to changes in the environment. This paper presents a discriminative incremental learning approach to place recognition. We use a recently introduced version of the incremental SVM, which ...
Bayesian logistic regression analysis
Van Erp, H.R.N.; Van Gelder, P.H.A.J.M.
2012-01-01
In this paper we present a Bayesian logistic regression analysis. It is found that if one wishes to derive the posterior distribution of the probability of some event, then, together with the traditional Bayes Theorem and the integrating out of nuissance parameters, the Jacobian transformation is an
Bayesian Geostatistical Design
DEFF Research Database (Denmark)
Diggle, Peter; Lophaven, Søren Nymand
2006-01-01
locations to, or deletion of locations from, an existing design, and prospective design, which consists of choosing positions for a new set of sampling locations. We propose a Bayesian design criterion which focuses on the goal of efficient spatial prediction whilst allowing for the fact that model...
Bayesian statistical inference
Directory of Open Access Journals (Sweden)
Bruno De Finetti
2017-04-01
Full Text Available This work was translated into English and published in the volume: Bruno De Finetti, Induction and Probability, Biblioteca di Statistica, eds. P. Monari, D. Cocchi, Clueb, Bologna, 1993.Bayesian statistical Inference is one of the last fundamental philosophical papers in which we can find the essential De Finetti's approach to the statistical inference.
DEFF Research Database (Denmark)
Hartelius, Karsten; Carstensen, Jens Michael
2003-01-01
A method for locating distorted grid structures in images is presented. The method is based on the theories of template matching and Bayesian image restoration. The grid is modeled as a deformable template. Prior knowledge of the grid is described through a Markov random field (MRF) model which r...
Bayesian Independent Component Analysis
DEFF Research Database (Denmark)
Winther, Ole; Petersen, Kaare Brandt
2007-01-01
In this paper we present an empirical Bayesian framework for independent component analysis. The framework provides estimates of the sources, the mixing matrix and the noise parameters, and is flexible with respect to choice of source prior and the number of sources and sensors. Inside the engine...
Bayesian Exponential Smoothing.
Forbes, C.S.; Snyder, R.D.; Shami, R.S.
2000-01-01
In this paper, a Bayesian version of the exponential smoothing method of forecasting is proposed. The approach is based on a state space model containing only a single source of error for each time interval. This model allows us to improve current practices surrounding exponential smoothing by providing both point predictions and measures of the uncertainty surrounding them.
Attention in a bayesian framework
DEFF Research Database (Denmark)
Whiteley, Louise Emma; Sahani, Maneesh
2012-01-01
, and include both selective phenomena, where attention is invoked by cues that point to particular stimuli, and integrative phenomena, where attention is invoked dynamically by endogenous processing. However, most previous Bayesian accounts of attention have focused on describing relatively simple experimental...... selective and integrative roles, and thus cannot be easily extended to complex environments. We suggest that the resource bottleneck stems from the computational intractability of exact perceptual inference in complex settings, and that attention reflects an evolved mechanism for approximate inference which...... can be shaped to refine the local accuracy of perception. We show that this approach extends the simple picture of attention as prior, so as to provide a unified and computationally driven account of both selective and integrative attentional phenomena....
Dynamic gradient descent learning algorithms for enhanced empirical modeling of power plants
International Nuclear Information System (INIS)
Parlos, A.G.; Atiya, Amir; Chong, K.T.
1991-01-01
A newly developed dynamic gradient descent-based learning algorithm is used to train a recurrent multilayer perceptron network for use in empirical modeling of power plants. The two main advantages of the proposed learning algorithm are its ability to consider past error gradient information for future use and the two forward passes associated with its implementation, instead of one forward and one backward pass of the backpropagation algorithm. The latter advantage results in computational time saving because both passes can be performed simultaneously. The dynamic learning algorithm is used to train a hybrid feedforward/feedback neural network, a recurrent multilayer perceptron, which was previously found to exhibit good interpolation and extrapolation capabilities in modeling nonlinear dynamic systems. One of the drawbacks, however, of the previously reported work has been the long training times associated with accurate empirical models. The enhanced learning capabilities provided by the dynamic gradient descent-based learning algorithm are demonstrated by a case study of a steam power plant. The number of iterations required for accurate empirical modeling has been reduced from tens of thousands to hundreds, thus significantly expediting the learning process
Energy Technology Data Exchange (ETDEWEB)
Denman, Matthew R. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Groth, Katrina M. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Cardoni, Jeffrey N. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Wheeler, Timothy A. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
2015-04-01
Accident management is an important component to maintaining risk at acceptable levels for all complex systems, such as nuclear power plants. With the introduction of self-correcting, or inherently safe, reactor designs the focus has shifted from management by operators to allowing the system's design to manage the accident. Inherently and passively safe designs are laudable, but nonetheless extreme boundary conditions can interfere with the design attributes which facilitate inherent safety, thus resulting in unanticipated and undesirable end states. This report examines an inherently safe and small sodium fast reactor experiencing a beyond design basis seismic event with the intend of exploring two issues : (1) can human intervention either improve or worsen the potential end states and (2) can a Bayesian Network be constructed to infer the state of the reactor to inform (1). ACKNOWLEDGEMENTS The authors would like to acknowledge the U.S. Department of Energy's Office of Nuclear Energy for funding this research through Work Package SR-14SN100303 under the Advanced Reactor Concepts program. The authors also acknowledge the PRA teams at Argonne National Laboratory, Oak Ridge National Laboratory, and Idaho National Laboratory for their continue d contributions to the advanced reactor PRA mission area.
The emergence of learning-teaching trajectories in education: a complex dynamic systems approach.
Steenbeek, Henderien; van Geert, Paul
2013-04-01
In this article we shall focus on learning-teaching trajectories ='successful' as well as 'unsuccessful' ones - as emergent and dynamic phenomena resulting from the interactions in the entire educational context, in particular the interaction between students and teachers viewed as processes of intertwining self-, other- and co-regulation. The article provides a review of the educational research literature on action regulation in learning and teaching, and interprets this literature in light of the theory of complex dynamic systems. Based on this reinterpretation of the literature, two dynamic models are proposed, one focusing on the short-term dynamics of learning-teaching interactions as they take place in classrooms, the other focusing on the long-term dynamics of interactions in a network of variables encompassing concerns, evaluations, actions and action effects (such as learning) students and teachers. The aim of presenting these models is to demonstrate, first, the possibility of transforming existing educational theory into dynamic models and, second, to provide some suggestions as to how such models can be used to further educational theory and practice.
Bayesian approach and application to operation safety
International Nuclear Information System (INIS)
Procaccia, H.; Suhner, M.Ch.
2003-01-01
The management of industrial risks requires the development of statistical and probabilistic analyses which use all the available convenient information in order to compensate the insufficient experience feedback in a domain where accidents and incidents remain too scarce to perform a classical statistical frequency analysis. The Bayesian decision approach is well adapted to this problem because it integrates both the expertise and the experience feedback. The domain of knowledge is widen, the forecasting study becomes possible and the decisions-remedial actions are strengthen thanks to risk-cost-benefit optimization analyzes. This book presents the bases of the Bayesian approach and its concrete applications in various industrial domains. After a mathematical presentation of the industrial operation safety concepts and of the Bayesian approach principles, this book treats of some of the problems that can be solved thanks to this approach: softwares reliability, controls linked with the equipments warranty, dynamical updating of databases, expertise modeling and weighting, Bayesian optimization in the domains of maintenance, quality control, tests and design of new equipments. A synthesis of the mathematical formulae used in this approach is given in conclusion. (J.S.)
Dynamic functional brain networks involved in simple visual discrimination learning.
Fidalgo, Camino; Conejo, Nélida María; González-Pardo, Héctor; Arias, Jorge Luis
2014-10-01
Visual discrimination tasks have been widely used to evaluate many types of learning and memory processes. However, little is known about the brain regions involved at different stages of visual discrimination learning. We used cytochrome c oxidase histochemistry to evaluate changes in regional brain oxidative metabolism during visual discrimination learning in a water-T maze at different time points during training. As compared with control groups, the results of the present study reveal the gradual activation of cortical (prefrontal and temporal cortices) and subcortical brain regions (including the striatum and the hippocampus) associated to the mastery of a simple visual discrimination task. On the other hand, the brain regions involved and their functional interactions changed progressively over days of training. Regions associated with novelty, emotion, visuo-spatial orientation and motor aspects of the behavioral task seem to be relevant during the earlier phase of training, whereas a brain network comprising the prefrontal cortex was found along the whole learning process. This study highlights the relevance of functional interactions among brain regions to investigate learning and memory processes. Copyright © 2014 Elsevier Inc. All rights reserved.
Directory of Open Access Journals (Sweden)
Pengpeng Jiao
2014-01-01
Full Text Available Time-dependent turning movement flows are very important input data for intelligent transportation systems but are impossible to be detected directly through current traffic surveillance systems. Existing estimation models have proved to be not accurate and reliable enough during all intervals. An improved way to address this problem is to develop a combined model framework that can integrate multiple submodels running simultaneously. This paper first presents a back propagation neural network model to estimate dynamic turning movements, as well as the self-adaptive learning rate approach and the gradient descent with momentum method for solving. Second, this paper develops an efficient Kalman filtering model and designs a revised sequential Kalman filtering algorithm. Based on the Bayesian method using both historical data and currently estimated results for error calibration, this paper further integrates above two submodels into a Bayesian combined model framework and proposes a corresponding algorithm. A field survey is implemented at an intersection in Beijing city to collect both time series of link counts and actual time-dependent turning movement flows, including historical and present data. The reported estimation results show that the Bayesian combined model is much more accurate and stable than other models.
An online learning approach to dynamic pricing for demand response
Jia, Liyan; Tong, Lang; Zhao, Qing
2014-01-01
In this paper, the problem of optimal dynamic pricing for retail electricity with an unknown demand model is considered. Under the day-ahead dynamic pricing (a.k.a. real time pricing) mechanism, a retailer obtains electricity in a twosettlement wholesale market and serves its customers in real time. Without knowledge on the aggregated demand function of its customers, the retailer aims to maximize its retail surplus by sequentially adjusting its price based on the behavior of its customers in...
A Neural Network Model to Learn Multiple Tasks under Dynamic Environments
Tsumori, Kenji; Ozawa, Seiichi
When environments are dynamically changed for agents, the knowledge acquired in an environment might be useless in future. In such dynamic environments, agents should be able to not only acquire new knowledge but also modify old knowledge in learning. However, modifying all knowledge acquired before is not efficient because the knowledge once acquired may be useful again when similar environment reappears and some knowledge can be shared among different environments. To learn efficiently in such environments, we propose a neural network model that consists of the following modules: resource allocating network, long-term & short-term memory, and environment change detector. We evaluate the model under a class of dynamic environments where multiple function approximation tasks are sequentially given. The experimental results demonstrate that the proposed model possesses stable incremental learning, accurate environmental change detection, proper association and recall of old knowledge, and efficient knowledge transfer.
The role of visual representation in physics learning: dynamic versus static visualization
Suyatna, Agus; Anggraini, Dian; Agustina, Dina; Widyastuti, Dini
2017-11-01
This study aims to examine the role of visual representation in physics learning and to compare the learning outcomes of using dynamic and static visualization media. The study was conducted using quasi-experiment with Pretest-Posttest Control Group Design. The samples of this research are students of six classes at State Senior High School in Lampung Province. The experimental class received a learning using dynamic visualization and control class using static visualization media. Both classes are given pre-test and post-test with the same instruments. Data were tested with N-gain analysis, normality test, homogeneity test and mean difference test. The results showed that there was a significant increase of mean (N-Gain) learning outcomes (p physical phenomena and requires long-term observation.
A tutorial introduction to Bayesian models of cognitive development.
Perfors, Amy; Tenenbaum, Joshua B; Griffiths, Thomas L; Xu, Fei
2011-09-01
We present an introduction to Bayesian inference as it is used in probabilistic models of cognitive development. Our goal is to provide an intuitive and accessible guide to the what, the how, and the why of the Bayesian approach: what sorts of problems and data the framework is most relevant for, and how and why it may be useful for developmentalists. We emphasize a qualitative understanding of Bayesian inference, but also include information about additional resources for those interested in the cognitive science applications, mathematical foundations, or machine learning details in more depth. In addition, we discuss some important interpretation issues that often arise when evaluating Bayesian models in cognitive science. Copyright © 2010 Elsevier B.V. All rights reserved.
Directory of Open Access Journals (Sweden)
Patrick G T Walker
2010-02-01
Full Text Available Outbreaks of H5N1 in poultry in Vietnam continue to threaten the livelihoods of those reliant on poultry production whilst simultaneously posing a severe public health risk given the high mortality associated with human infection. Authorities have invested significant resources in order to control these outbreaks. Of particular interest is the decision, following a second wave of outbreaks, to move from a "stamping out" approach to the implementation of a nationwide mass vaccination campaign. Outbreaks which occurred around this shift in policy provide a unique opportunity to evaluate the relative effectiveness of these approaches and to help other countries make informed judgements when developing control strategies. Here we use Bayesian Markov Chain Monte Carlo (MCMC data augmentation techniques to derive the first quantitative estimates of the impact of the vaccination campaign on the spread of outbreaks of H5N1 in northern Vietnam. We find a substantial decrease in the transmissibility of infection between communes following vaccination. This was coupled with a significant increase in the time from infection to detection of the outbreak. Using a cladistic approach we estimated that, according to the posterior mean effect of pruning the reconstructed epidemic tree, two thirds of the outbreaks in 2007 could be attributed to this decrease in the rate of reporting. The net impact of these two effects was a less intense but longer-lasting wave and, whilst not sufficient to prevent the sustained spread of outbreaks, an overall reduction in the likelihood of the transmission of infection between communes. These findings highlight the need for more effectively targeted surveillance in order to help ensure that the effective coverage achieved by mass vaccination is converted into a reduction in the likelihood of outbreaks occurring which is sufficient to control the spread of H5N1 in Vietnam.
Learning Constructive Primitives for Real-time Dynamic Difficulty Adjustment in Super Mario Bros
Shi, Peizhi; Chen, Ke
2017-01-01
Among the main challenges in procedural content generation (PCG), content quality assurance and dynamic difficulty adjustment (DDA) of game content in real time are two major issues concerned in adaptive content generation. Motivated by the recent learning-based PCG framework, we propose a novel approach to seamlessly address two issues in Super Mario Bros (SMB). To address the quality assurance issue, we exploit the synergy between rule-based and learning-based methods to produce quality gam...
Virkar, Yogesh S.; Shew, Woodrow L.; Restrepo, Juan G.; Ott, Edward
2016-10-01
Learning and memory are acquired through long-lasting changes in synapses. In the simplest models, such synaptic potentiation typically leads to runaway excitation, but in reality there must exist processes that robustly preserve overall stability of the neural system dynamics. How is this accomplished? Various approaches to this basic question have been considered. Here we propose a particularly compelling and natural mechanism for preserving stability of learning neural systems. This mechanism is based on the global processes by which metabolic resources are distributed to the neurons by glial cells. Specifically, we introduce and study a model composed of two interacting networks: a model neural network interconnected by synapses that undergo spike-timing-dependent plasticity; and a model glial network interconnected by gap junctions that diffusively transport metabolic resources among the glia and, ultimately, to neural synapses where they are consumed. Our main result is that the biophysical constraints imposed by diffusive transport of metabolic resources through the glial network can prevent runaway growth of synaptic strength, both during ongoing activity and during learning. Our findings suggest a previously unappreciated role for glial transport of metabolites in the feedback control stabilization of neural network dynamics during learning.
Yuan, Chengzhi; Licht, Stephen; He, Haibo
2017-09-26
In this paper, a new concept of formation learning control is introduced to the field of formation control of multiple autonomous underwater vehicles (AUVs), which specifies a joint objective of distributed formation tracking control and learning/identification of nonlinear uncertain AUV dynamics. A novel two-layer distributed formation learning control scheme is proposed, which consists of an upper-layer distributed adaptive observer and a lower-layer decentralized deterministic learning controller. This new formation learning control scheme advances existing techniques in three important ways: 1) the multi-AUV system under consideration has heterogeneous nonlinear uncertain dynamics; 2) the formation learning control protocol can be designed and implemented by each local AUV agent in a fully distributed fashion without using any global information; and 3) in addition to the formation control performance, the distributed control protocol is also capable of accurately identifying the AUVs' heterogeneous nonlinear uncertain dynamics and utilizing experiences to improve formation control performance. Extensive simulations have been conducted to demonstrate the effectiveness of the proposed results.
Probability and Bayesian statistics
1987-01-01
This book contains selected and refereed contributions to the "Inter national Symposium on Probability and Bayesian Statistics" which was orga nized to celebrate the 80th birthday of Professor Bruno de Finetti at his birthplace Innsbruck in Austria. Since Professor de Finetti died in 1985 the symposium was dedicated to the memory of Bruno de Finetti and took place at Igls near Innsbruck from 23 to 26 September 1986. Some of the pa pers are published especially by the relationship to Bruno de Finetti's scientific work. The evolution of stochastics shows growing importance of probability as coherent assessment of numerical values as degrees of believe in certain events. This is the basis for Bayesian inference in the sense of modern statistics. The contributions in this volume cover a broad spectrum ranging from foundations of probability across psychological aspects of formulating sub jective probability statements, abstract measure theoretical considerations, contributions to theoretical statistics an...
DEFF Research Database (Denmark)
Mørup, Morten; Schmidt, Mikkel N
2012-01-01
Many networks of scientific interest naturally decompose into clusters or communities with comparatively fewer external than internal links; however, current Bayesian models of network communities do not exert this intuitive notion of communities. We formulate a nonparametric Bayesian model...... for community detection consistent with an intuitive definition of communities and present a Markov chain Monte Carlo procedure for inferring the community structure. A Matlab toolbox with the proposed inference procedure is available for download. On synthetic and real networks, our model detects communities...... consistent with ground truth, and on real networks, it outperforms existing approaches in predicting missing links. This suggests that community structure is an important structural property of networks that should be explicitly modeled....
Bayesian analogy with relational transformations.
Lu, Hongjing; Chen, Dawn; Holyoak, Keith J
2012-07-01
How can humans acquire relational representations that enable analogical inference and other forms of high-level reasoning? Using comparative relations as a model domain, we explore the possibility that bottom-up learning mechanisms applied to objects coded as feature vectors can yield representations of relations sufficient to solve analogy problems. We introduce Bayesian analogy with relational transformations (BART) and apply the model to the task of learning first-order comparative relations (e.g., larger, smaller, fiercer, meeker) from a set of animal pairs. Inputs are coded by vectors of continuous-valued features, based either on human magnitude ratings, normed feature ratings (De Deyne et al., 2008), or outputs of the topics model (Griffiths, Steyvers, & Tenenbaum, 2007). Bootstrapping from empirical priors, the model is able to induce first-order relations represented as probabilistic weight distributions, even when given positive examples only. These learned representations allow classification of novel instantiations of the relations and yield a symbolic distance effect of the sort obtained with both humans and other primates. BART then transforms its learned weight distributions by importance-guided mapping, thereby placing distinct dimensions into correspondence. These transformed representations allow BART to reliably solve 4-term analogies (e.g., larger:smaller::fiercer:meeker), a type of reasoning that is arguably specific to humans. Our results provide a proof-of-concept that structured analogies can be solved with representations induced from unstructured feature vectors by mechanisms that operate in a largely bottom-up fashion. We discuss potential implications for algorithmic and neural models of relational thinking, as well as for the evolution of abstract thought. Copyright 2012 APA, all rights reserved.
Bayesian Modelling of Functional Whole Brain Connectivity
DEFF Research Database (Denmark)
Røge, Rasmus
the prevalent strategy of standardizing of fMRI time series and model data using directional statistics or we model the variability in the signal across the brain and across multiple subjects. In either case, we use Bayesian nonparametric modeling to automatically learn from the fMRI data the number......This thesis deals with parcellation of whole-brain functional magnetic resonance imaging (fMRI) using Bayesian inference with mixture models tailored to the fMRI data. In the three included papers and manuscripts, we analyze two different approaches to modeling fMRI signal; either we accept...... of funcional units, i.e. parcels. We benchmark the proposed mixture models against state of the art methods of brain parcellation, both probabilistic and non-probabilistic. The time series of each voxel are most often standardized using z-scoring which projects the time series data onto a hypersphere...
Bayesian network modelling of upper gastrointestinal bleeding
Aisha, Nazziwa; Shohaimi, Shamarina; Adam, Mohd Bakri
2013-09-01
Bayesian networks are graphical probabilistic models that represent causal and other relationships between domain variables. In the context of medical decision making, these models have been explored to help in medical diagnosis and prognosis. In this paper, we discuss the Bayesian network formalism in building medical support systems and we learn a tree augmented naive Bayes Network (TAN) from gastrointestinal bleeding data. The accuracy of the TAN in classifying the source of gastrointestinal bleeding into upper or lower source is obtained. The TAN achieves a high classification accuracy of 86% and an area under curve of 92%. A sensitivity analysis of the model shows relatively high levels of entropy reduction for color of the stool, history of gastrointestinal bleeding, consistency and the ratio of blood urea nitrogen to creatinine. The TAN facilitates the identification of the source of GIB and requires further validation.
Approximate Bayesian recursive estimation
Czech Academy of Sciences Publication Activity Database
Kárný, Miroslav
2014-01-01
Roč. 285, č. 1 (2014), s. 100-111 ISSN 0020-0255 R&D Projects: GA ČR GA13-13502S Institutional support: RVO:67985556 Keywords : Approximate parameter estimation * Bayesian recursive estimation * Kullback–Leibler divergence * Forgetting Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 4.038, year: 2014 http://library.utia.cas.cz/separaty/2014/AS/karny-0425539.pdf
DEFF Research Database (Denmark)
Antoniou, Constantinos; Harrison, Glenn W.; Lau, Morten I.
2015-01-01
A large literature suggests that many individuals do not apply Bayes’ Rule when making decisions that depend on them correctly pooling prior information and sample data. We replicate and extend a classic experimental study of Bayesian updating from psychology, employing the methods of experimenta...... economics, with careful controls for the confounding effects of risk aversion. Our results show that risk aversion significantly alters inferences on deviations from Bayes’ Rule....
Energy Technology Data Exchange (ETDEWEB)
Andrews, Stephen A. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Sigeti, David E. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
2017-11-15
These are a set of slides about Bayesian hypothesis testing, where many hypotheses are tested. The conclusions are the following: The value of the Bayes factor obtained when using the median of the posterior marginal is almost the minimum value of the Bayes factor. The value of τ^{2} which minimizes the Bayes factor is a reasonable choice for this parameter. This allows a likelihood ratio to be computed with is the least favorable to H_{0}.
Introduction to Bayesian statistics
Koch, Karl-Rudolf
2007-01-01
This book presents Bayes' theorem, the estimation of unknown parameters, the determination of confidence regions and the derivation of tests of hypotheses for the unknown parameters. It does so in a simple manner that is easy to comprehend. The book compares traditional and Bayesian methods with the rules of probability presented in a logical way allowing an intuitive understanding of random variables and their probability distributions to be formed.
Bayesian theory and applications
Dellaportas, Petros; Polson, Nicholas G; Stephens, David A
2013-01-01
The development of hierarchical models and Markov chain Monte Carlo (MCMC) techniques forms one of the most profound advances in Bayesian analysis since the 1970s and provides the basis for advances in virtually all areas of applied and theoretical Bayesian statistics. This volume guides the reader along a statistical journey that begins with the basic structure of Bayesian theory, and then provides details on most of the past and present advances in this field. The book has a unique format. There is an explanatory chapter devoted to each conceptual advance followed by journal-style chapters that provide applications or further advances on the concept. Thus, the volume is both a textbook and a compendium of papers covering a vast range of topics. It is appropriate for a well-informed novice interested in understanding the basic approach, methods and recent applications. Because of its advanced chapters and recent work, it is also appropriate for a more mature reader interested in recent applications and devel...
Dynamic e-learning modules for student lecture preparation
Directory of Open Access Journals (Sweden)
Timothy McIntyre
2018-03-01
Full Text Available We have developed and demonstrated the effectiveness of a set of online interactive learning modules to accompany physics courses at first- and second-year university levels. Students access the modules prior to attending lectures to familiarize themselves with content which is then discussed and reaffirmed in class. Student surveys and access data show that students were much more likely to use material presented in this form, rather than a textbook, when preparing for lectures given in an active learning format. The students found that interactive simulations, videos of problem-solving approaches prepared by course staff, and quick-check immediate feedback questions were all useful tools for lecture preparation–none of which are available when using a traditional textbook for lecture preparation.