Learning conditional Gaussian networks

DEFF Research Database (Denmark)

Bøttcher, Susanne Gammelgaard

This paper considers conditional Gaussian networks. The parameters in the network are learned by using conjugate Bayesian analysis. As conjugate local priors, we apply the Dirichlet distribution for discrete variables and the Gaussian-inverse gamma distribution for continuous variables, given...... a configuration of the discrete parents. We assume parameter independence and complete data. Further, to learn the structure of the network, the network score is deduced. We then develop a local master prior procedure, for deriving parameter priors in these networks. This procedure satisfies parameter...... independence, parameter modularity and likelihood equivalence. Bayes factors to be used in model search are introduced. Finally the methods derived are illustrated by a simple example....

An Analysis of Density and Degree-Centrality According to the Social Networking Structure Formed in an Online Learning Environment

Science.gov (United States)

Ergün, Esin; Usluel, Yasemin Koçak

2016-01-01

In this study, we assessed the communication structure in an educational online learning environment using social network analysis (SNA). The communication structure was examined with respect to time, and instructor's participation. The course was implemented using ELGG, a network learning environment, blended with face-to-face sessions over a…

Neural-Fitted TD-Leaf Learning for Playing Othello With Structured Neural Networks

NARCIS (Netherlands)

van den Dries, Sjoerd; Wiering, Marco A.

This paper describes a methodology for quickly learning to play games at a strong level. The methodology consists of a novel combination of three techniques, and a variety of experiments on the game of Othello demonstrates their usefulness. First, structures or topologies in neural network

Adaptive neural network/expert system that learns fault diagnosis for different structures

Science.gov (United States)

Simon, Solomon H.

1992-08-01

Corporations need better real-time monitoring and control systems to improve productivity by watching quality and increasing production flexibility. The innovative technology to achieve this goal is evolving in the form artificial intelligence and neural networks applied to sensor processing, fusion, and interpretation. By using these advanced Al techniques, we can leverage existing systems and add value to conventional techniques. Neural networks and knowledge-based expert systems can be combined into intelligent sensor systems which provide real-time monitoring, control, evaluation, and fault diagnosis for production systems. Neural network-based intelligent sensor systems are more reliable because they can provide continuous, non-destructive monitoring and inspection. Use of neural networks can result in sensor fusion and the ability to model highly, non-linear systems. Improved models can provide a foundation for more accurate performance parameters and predictions. We discuss a research software/hardware prototype which integrates neural networks, expert systems, and sensor technologies and which can adapt across a variety of structures to perform fault diagnosis. The flexibility and adaptability of the prototype in learning two structures is presented. Potential applications are discussed.

Learning and structure of neuronal networks

Indian Academy of Sciences (India)

structures, protein–protein interaction networks, social interactions, the Internet, and so on can be described by complex networks [1–5]. Recent developments in the understanding of complex networks has led to deeper insights about their origin and other properties [1–5]. One common realization that emerges from these ...

Evolution of individual versus social learning on social networks.

Science.gov (United States)

Tamura, Kohei; Kobayashi, Yutaka; Ihara, Yasuo

2015-03-06

A number of studies have investigated the roles played by individual and social learning in cultural phenomena and the relative advantages of the two learning strategies in variable environments. Because social learning involves the acquisition of behaviours from others, its utility depends on the availability of 'cultural models' exhibiting adaptive behaviours. This indicates that social networks play an essential role in the evolution of learning. However, possible effects of social structure on the evolution of learning have not been fully explored. Here, we develop a mathematical model to explore the evolutionary dynamics of learning strategies on social networks. We first derive the condition under which social learners (SLs) are selectively favoured over individual learners in a broad range of social network. We then obtain an analytical approximation of the long-term average frequency of SLs in homogeneous networks, from which we specify the condition, in terms of three relatedness measures, for social structure to facilitate the long-term evolution of social learning. Finally, we evaluate our approximation by Monte Carlo simulations in complete graphs, regular random graphs and scale-free networks. We formally show that whether social structure favours the evolution of social learning is determined by the relative magnitudes of two effects of social structure: localization in competition, by which competition between learning strategies is evaded, and localization in cultural transmission, which slows down the spread of adaptive traits. In addition, our estimates of the relatedness measures suggest that social structure disfavours the evolution of social learning when selection is weak. © 2015 The Author(s) Published by the Royal Society. All rights reserved.

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...

Structure Learning and Statistical Estimation in Distribution Networks - Part I

Energy Technology Data Exchange (ETDEWEB)

Deka, Deepjyoti [Univ. of Texas, Austin, TX (United States); Backhaus, Scott N. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Chertkov, Michael [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

2015-02-13

Traditionally power distribution networks are either not observable or only partially observable. This complicates development and implementation of new smart grid technologies, such as those related to demand response, outage detection and management, and improved load-monitoring. In this two part paper, inspired by proliferation of the metering technology, we discuss estimation problems in structurally loopy but operationally radial distribution grids from measurements, e.g. voltage data, which are either already available or can be made available with a relatively minor investment. In Part I, the objective is to learn the operational layout of the grid. Part II of this paper presents algorithms that estimate load statistics or line parameters in addition to learning the grid structure. Further, Part II discusses the problem of structure estimation for systems with incomplete measurement sets. Our newly suggested algorithms apply to a wide range of realistic scenarios. The algorithms are also computationally efficient – polynomial in time– which is proven theoretically and illustrated computationally on a number of test cases. The technique developed can be applied to detect line failures in real time as well as to understand the scope of possible adversarial attacks on the grid.

A Collaborative Learning Network Approach to Improvement: The CUSP Learning Network.

Science.gov (United States)

Weaver, Sallie J; Lofthus, Jennifer; Sawyer, Melinda; Greer, Lee; Opett, Kristin; Reynolds, Catherine; Wyskiel, Rhonda; Peditto, Stephanie; Pronovost, Peter J

2015-04-01

Collaborative improvement networks draw on the science of collaborative organizational learning and communities of practice to facilitate peer-to-peer learning, coaching, and local adaption. Although significant improvements in patient safety and quality have been achieved through collaborative methods, insight regarding how collaborative networks are used by members is needed. Improvement Strategy: The Comprehensive Unit-based Safety Program (CUSP) Learning Network is a multi-institutional collaborative network that is designed to facilitate peer-to-peer learning and coaching specifically related to CUSP. Member organizations implement all or part of the CUSP methodology to improve organizational safety culture, patient safety, and care quality. Qualitative case studies developed by participating members examine the impact of network participation across three levels of analysis (unit, hospital, health system). In addition, results of a satisfaction survey designed to evaluate member experiences were collected to inform network development. Common themes across case studies suggest that members found value in collaborative learning and sharing strategies across organizational boundaries related to a specific improvement strategy. The CUSP Learning Network is an example of network-based collaborative learning in action. Although this learning network focuses on a particular improvement methodology-CUSP-there is clear potential for member-driven learning networks to grow around other methods or topic areas. Such collaborative learning networks may offer a way to develop an infrastructure for longer-term support of improvement efforts and to more quickly diffuse creative sustainment strategies.

Quantitative learning strategies based on word networks

Science.gov (United States)

Zhao, Yue-Tian-Yi; Jia, Zi-Yang; Tang, Yong; Xiong, Jason Jie; Zhang, Yi-Cheng

2018-02-01

Learning English requires a considerable effort, but the way that vocabulary is introduced in textbooks is not optimized for learning efficiency. With the increasing population of English learners, learning process optimization will have significant impact and improvement towards English learning and teaching. The recent developments of big data analysis and complex network science provide additional opportunities to design and further investigate the strategies in English learning. In this paper, quantitative English learning strategies based on word network and word usage information are proposed. The strategies integrate the words frequency with topological structural information. By analyzing the influence of connected learned words, the learning weights for the unlearned words and dynamically updating of the network are studied and analyzed. The results suggest that quantitative strategies significantly improve learning efficiency while maintaining effectiveness. Especially, the optimized-weight-first strategy and segmented strategies outperform other strategies. The results provide opportunities for researchers and practitioners to reconsider the way of English teaching and designing vocabularies quantitatively by balancing the efficiency and learning costs based on the word network.

Redes de aprendizaje, aprendizaje en red Learning Networks, Networked Learning

Directory of Open Access Journals (Sweden)

Peter Sloep

2011-10-01

Full Text Available Las redes de aprendizaje (Learning Networks son redes sociales en línea mediante las cuales los participantes comparten información y colaboran para crear conocimiento. De esta manera, estas redes enriquecen la experiencia de aprendizaje en cualquier contexto de aprendizaje, ya sea de educación formal (en escuelas o universidades o educación no-formal (formación profesional. Aunque el concepto de aprendizaje en red suscita el interés de diferentes actores del ámbito educativo, aún existen muchos interrogantes sobre cómo debe diseñarse el aprendizaje en red para facilitar adecuadamente la educación y la formación. El artículo toma este interrogante como punto de partida, y posteriormente aborda cuestiones como la dinámica de la evolución de las redes de aprendizaje, la importancia de fomentar la confianza entre los participantes y el papel central que desempeña el perfil de usuario en la construcción de la confianza, así como el apoyo entre compañeros. Además, se elabora el proceso de diseño de una red de aprendizaje, y se describe un ejemplo en el contexto universitario. Basándonos en la investigación que actualmente se lleva a cabo en nuestro propio centro y en otros lugares, el capítulo concluye con una visión del futuro de las redes de aprendizaje.Learning Networks are on-line social networks through which users share knowledge with each other and jointly develop new knowledge. This way, Learning Networks may enrich the experience of formal, school-based learning and form a viable setting for professional development. Although networked learning enjoys an increasing interest, many questions remain on how exactly learning in such networked contexts can contribute to successful education and training. Put differently, how should networked learning be designed best to facilitate education and training? Taking this as its point of departure, the chapter addresses such issues as the dynamic evolution of Learning Networks

Learning and Model-checking Networks of I/O Automata

DEFF Research Database (Denmark)

Mao, Hua; Jaeger, Manfred

2012-01-01

We introduce a new statistical relational learning (SRL) approach in which models for structured data, especially network data, are constructed as networks of communicating nite probabilistic automata. Leveraging existing automata learning methods from the area of grammatical inference, we can...... learn generic models for network entities in the form of automata templates. As is characteristic for SRL techniques, the abstraction level aorded by learning generic templates enables one to apply the learned model to new domains. A main benet of learning models based on nite automata lies in the fact...

Efficient learning strategy of Chinese characters based on network approach.

Directory of Open Access Journals (Sweden)

Xiaoyong Yan

Full Text Available We develop an efficient learning strategy of Chinese characters based on the network of the hierarchical structural relations between Chinese characters. A more efficient strategy is that of learning the same number of useful Chinese characters in less effort or time. We construct a node-weighted network of Chinese characters, where character usage frequencies are used as node weights. Using this hierarchical node-weighted network, we propose a new learning method, the distributed node weight (DNW strategy, which is based on a new measure of nodes' importance that considers both the weight of the nodes and its location in the network hierarchical structure. Chinese character learning strategies, particularly their learning order, are analyzed as dynamical processes over the network. We compare the efficiency of three theoretical learning methods and two commonly used methods from mainstream Chinese textbooks, one for Chinese elementary school students and the other for students learning Chinese as a second language. We find that the DNW method significantly outperforms the others, implying that the efficiency of current learning methods of major textbooks can be greatly improved.

A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks.

Science.gov (United States)

Siri, Benoît; Berry, Hugues; Cessac, Bruno; Delord, Bruno; Quoy, Mathias

2008-12-01

We present a mathematical analysis of the effects of Hebbian learning in random recurrent neural networks, with a generic Hebbian learning rule, including passive forgetting and different timescales, for neuronal activity and learning dynamics. Previous numerical work has reported that Hebbian learning drives the system from chaos to a steady state through a sequence of bifurcations. Here, we interpret these results mathematically and show that these effects, involving a complex coupling between neuronal dynamics and synaptic graph structure, can be analyzed using Jacobian matrices, which introduce both a structural and a dynamical point of view on neural network evolution. Furthermore, we show that sensitivity to a learned pattern is maximal when the largest Lyapunov exponent is close to 0. We discuss how neural networks may take advantage of this regime of high functional interest.

Statistical and machine learning approaches for network analysis

CERN Document Server

Dehmer, Matthias

2012-01-01

Explore the multidisciplinary nature of complex networks through machine learning techniques Statistical and Machine Learning Approaches for Network Analysis provides an accessible framework for structurally analyzing graphs by bringing together known and novel approaches on graph classes and graph measures for classification. By providing different approaches based on experimental data, the book uniquely sets itself apart from the current literature by exploring the application of machine learning techniques to various types of complex networks. Comprised of chapters written by internation

Categorical Structure among Shared Features in Networks of Early-Learned Nouns

Science.gov (United States)

Hills, Thomas T.; Maouene, Mounir; Maouene, Josita; Sheya, Adam; Smith, Linda

2009-01-01

The shared features that characterize the noun categories that young children learn first are a formative basis of the human category system. To investigate the potential categorical information contained in the features of early-learned nouns, we examine the graph-theoretic properties of noun-feature networks. The networks are built from the…

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

Learning Analytics for Networked Learning Models

Science.gov (United States)

Joksimovic, Srecko; Hatala, Marek; Gaševic, Dragan

2014-01-01

Teaching and learning in networked settings has attracted significant attention recently. The central topic of networked learning research is human-human and human-information interactions occurring within a networked learning environment. The nature of these interactions is highly complex and usually requires a multi-dimensional approach to…

Learning Networks for Lifelong Learning

OpenAIRE

Sloep, Peter

2009-01-01

Presentation in a seminar organized by Christopher Hoadley at Penn State University, October 2004.Contains general introduction into the Learning Network Programme and a demonstration of the Netlogo Simulation of a Learning Network.

An empirical comparison of popular structure learning algorithms with a view to gene network inference

Czech Academy of Sciences Publication Activity Database

Djordjilović, V.; Chiogna, M.; Vomlel, Jiří

2017-01-01

Roč. 88, č. 1 (2017), s. 602-613 ISSN 0888-613X R&D Projects: GA ČR(CZ) GA16-12010S Institutional support: RVO:67985556 Keywords : Bayesian networks * Structure learning * Reverse engineering * Gene networks Subject RIV: JD - Computer Applications, Robotics OBOR OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) Impact factor: 2.845, year: 2016 http://library.utia.cas.cz/separaty/2017/MTR/vomlel-0477168.pdf

Social networks and performance in distributed learning communities

OpenAIRE

Cadima, Rita; Ojeda Rodríguez, Jordi; Monguet Fierro, José María

2012-01-01

Social networks play an essential role in learning environments as a key channel for knowledge sharing and students' support. In distributed learning communities, knowledge sharing does not occur as spontaneously as when a working group shares the same physical space; knowledge sharing depends even more on student informal connections. In this study we analyse two distributed learning communities' social networks in order to understand how characteristics of the social structure can enhance s...

A machine learning approach to automated structural network analysis: application to neonatal encephalopathy.

Directory of Open Access Journals (Sweden)

Etay Ziv

Full Text Available Neonatal encephalopathy represents a heterogeneous group of conditions associated with life-long developmental disabilities and neurological deficits. Clinical measures and current anatomic brain imaging remain inadequate predictors of outcome in children with neonatal encephalopathy. Some studies have suggested that brain development and, therefore, brain connectivity may be altered in the subgroup of patients who subsequently go on to develop clinically significant neurological abnormalities. Large-scale structural brain connectivity networks constructed using diffusion tractography have been posited to reflect organizational differences in white matter architecture at the mesoscale, and thus offer a unique tool for characterizing brain development in patients with neonatal encephalopathy. In this manuscript we use diffusion tractography to construct structural networks for a cohort of patients with neonatal encephalopathy. We systematically map these networks to a high-dimensional space and then apply standard machine learning algorithms to predict neurological outcome in the cohort. Using nested cross-validation we demonstrate high prediction accuracy that is both statistically significant and robust over a broad range of thresholds. Our algorithm offers a novel tool to evaluate neonates at risk for developing neurological deficit. The described approach can be applied to any brain pathology that affects structural connectivity.

The Structural Underpinnings of Policy Learning: A Classroom Policy Simulation

Science.gov (United States)

Bird, Stephen

This paper investigates the relationship between the centrality of individual actors in a social network structure and their policy learning performance. In a dynamic comparable to real-world policy networks, results from a classroom simulation demonstrate a strong relationship between centrality in social learning networks and grade performance. Previous research indicates that social network centrality should have a positive effect on learning in other contexts and this link is tested in a policy learning context. Second, the distinction between collaborative learning versus information diffusion processes in policy learning is examined. Third, frequency of interaction is analyzed to determine whether consistent, frequent tics have a greater impact on the learning process. Finally, the data arc analyzed to determine if the benefits of centrality have limitations or thresholds when benefits no longer accrue. These results demonstrate the importance of network structure, and support a collaborative conceptualization of the policy learning process.

Cross-linked structure of network evolution

International Nuclear Information System (INIS)

Bassett, Danielle S.; Wymbs, Nicholas F.; Grafton, Scott T.; Porter, Mason A.; Mucha, Peter J.

2014-01-01

We study the temporal co-variation of network co-evolution via the cross-link structure of networks, for which we take advantage of the formalism of hypergraphs to map cross-link structures back to network nodes. We investigate two sets of temporal network data in detail. In a network of coupled nonlinear oscillators, hyperedges that consist of network edges with temporally co-varying weights uncover the driving co-evolution patterns of edge weight dynamics both within and between oscillator communities. In the human brain, networks that represent temporal changes in brain activity during learning exhibit early co-evolution that then settles down with practice. Subsequent decreases in hyperedge size are consistent with emergence of an autonomous subgraph whose dynamics no longer depends on other parts of the network. Our results on real and synthetic networks give a poignant demonstration of the ability of cross-link structure to uncover unexpected co-evolution attributes in both real and synthetic dynamical systems. This, in turn, illustrates the utility of analyzing cross-links for investigating the structure of temporal networks

Cross-linked structure of network evolution

Energy Technology Data Exchange (ETDEWEB)

Bassett, Danielle S., E-mail: dsb@seas.upenn.edu [Department of Bioengineering, University of Pennsylvania, Philadelphia, Pennsylvania 19104 (United States); Department of Physics, University of California, Santa Barbara, California 93106 (United States); Sage Center for the Study of the Mind, University of California, Santa Barbara, California 93106 (United States); Wymbs, Nicholas F.; Grafton, Scott T. [Department of Psychology and UCSB Brain Imaging Center, University of California, Santa Barbara, California 93106 (United States); Porter, Mason A. [Oxford Centre for Industrial and Applied Mathematics, Mathematical Institute, University of Oxford, Oxford OX2 6GG (United Kingdom); CABDyN Complexity Centre, University of Oxford, Oxford, OX1 1HP (United Kingdom); Mucha, Peter J. [Carolina Center for Interdisciplinary Applied Mathematics, Department of Mathematics, University of North Carolina, Chapel Hill, North Carolina 27599 (United States); Department of Applied Physical Sciences, University of North Carolina, Chapel Hill, North Carolina 27599 (United States)

2014-03-15

We study the temporal co-variation of network co-evolution via the cross-link structure of networks, for which we take advantage of the formalism of hypergraphs to map cross-link structures back to network nodes. We investigate two sets of temporal network data in detail. In a network of coupled nonlinear oscillators, hyperedges that consist of network edges with temporally co-varying weights uncover the driving co-evolution patterns of edge weight dynamics both within and between oscillator communities. In the human brain, networks that represent temporal changes in brain activity during learning exhibit early co-evolution that then settles down with practice. Subsequent decreases in hyperedge size are consistent with emergence of an autonomous subgraph whose dynamics no longer depends on other parts of the network. Our results on real and synthetic networks give a poignant demonstration of the ability of cross-link structure to uncover unexpected co-evolution attributes in both real and synthetic dynamical systems. This, in turn, illustrates the utility of analyzing cross-links for investigating the structure of temporal networks.

Structural Plasticity Denoises Responses and Improves Learning Speed

Directory of Open Access Journals (Sweden)

Robin Spiess

2016-09-01

Full Text Available Despite an abundance of computational models for learning of synaptic weights, there has been relatively little research on structural plasticity, i.e. the creation and elimination of synapses. Especially, it is not clear how structural plasticity works in concert with spike-timing-dependent plasticity (STDP and what advantages their combination offers.Here we present a fairly large-scale functional model that uses leaky integrate-and-fire neurons, STDP, homeostasis, recurrent connections, and structural plasticity to learn the input encoding, the relation between inputs, and to infer missing inputs. Using this model, we compare the error and the amount of noise in the network's responses with and without structural plasticity and the influence of structural plasticity on the learning speed of the network.Using structural plasticity during learning shows good results for learning the representation of input values, i.e. structural plasticity strongly reduces the noise of the response by preventing spikes with a high error.For inferring missing inputs we see similar results, with responses having less noise if the network was trained using structural plasticity.Additionally, using structural plasticity with pruning significantly decreased the time to learn weights suitable for inference.Presumably, this is due to the clearer signal containing less spikes that misrepresent the desired value. Therefore, this work shows that structural plasticity is not only able to improve upon the performance using STDP without structural plasticity but also speeds up learning.Additionally, it addresses the practical problem of limited resources for connectivity that is not only apparent in the mammalian neocortex but also in computer hardware or neuromorphic (brain-inspired hardware by efficiently pruning synapses without losing performance.

Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks.

Science.gov (United States)

Nitta, Tohru

2017-10-01

We present a theoretical analysis of singular points of artificial deep neural networks, resulting in providing deep neural network models having no critical points introduced by a hierarchical structure. It is considered that such deep neural network models have good nature for gradient-based optimization. First, we show that there exist a large number of critical points introduced by a hierarchical structure in deep neural networks as straight lines, depending on the number of hidden layers and the number of hidden neurons. Second, we derive a sufficient condition for deep neural networks having no critical points introduced by a hierarchical structure, which can be applied to general deep neural networks. It is also shown that the existence of critical points introduced by a hierarchical structure is determined by the rank and the regularity of weight matrices for a specific class of deep neural networks. Finally, two kinds of implementation methods of the sufficient conditions to have no critical points are provided. One is a learning algorithm that can avoid critical points introduced by the hierarchical structure during learning (called avoidant learning algorithm). The other is a neural network that does not have some critical points introduced by the hierarchical structure as an inherent property (called avoidant neural network).

Reconstructing consensus Bayesian network structures with application to learning molecular interaction networks

NARCIS (Netherlands)

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

Distance metric learning for complex networks: Towards size-independent comparison of network structures

Science.gov (United States)

Aliakbary, Sadegh; Motallebi, Sadegh; Rashidian, Sina; Habibi, Jafar; Movaghar, Ali

2015-02-01

Real networks show nontrivial topological properties such as community structure and long-tail degree distribution. Moreover, many network analysis applications are based on topological comparison of complex networks. Classification and clustering of networks, model selection, and anomaly detection are just some applications of network comparison. In these applications, an effective similarity metric is needed which, given two complex networks of possibly different sizes, evaluates the amount of similarity between the structural features of the two networks. Traditional graph comparison approaches, such as isomorphism-based methods, are not only too time consuming but also inappropriate to compare networks with different sizes. In this paper, we propose an intelligent method based on the genetic algorithms for integrating, selecting, and weighting the network features in order to develop an effective similarity measure for complex networks. The proposed similarity metric outperforms state of the art methods with respect to different evaluation criteria.

Tracking influence between naive Bayes models using score-based structure learning

CSIR Research Space (South Africa)

Ajoodha, R

2017-11-01

Full Text Available Current structure learning practices in Bayesian networks have been developed to learn the structure between observable variables and learning latent parameters independently. One exception establishes a variant of EM for learning the structure...

Research, Boundaries, and Policy in Networked Learning

DEFF Research Database (Denmark)

This book presents cutting-edge, peer reviewed research on networked learning organized by three themes: policy in networked learning, researching networked learning, and boundaries in networked learning. The "policy in networked learning" section explores networked learning in relation to policy...... networks, spaces of algorithmic governance and more. The "boundaries in networked learning" section investigates frameworks of students' digital literacy practices, among other important frameworks in digital learning. Lastly, the "research in networked learning" section delves into new research methods...

SUSTAIN: a network model of category learning.

Science.gov (United States)

Love, Bradley C; Medin, Douglas L; Gureckis, Todd M

2004-04-01

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.

Conditions for Productive Learning in Network Learning Environments

DEFF Research Database (Denmark)

Ponti, M.; Dirckinck-Holmfeld, Lone; Lindström, B.

2004-01-01

are designed without a deep understanding of the pedagogical, communicative and collaborative conditions embedded in networked learning. Despite the existence of good theoretical views pointing to a social understanding of learning, rather than a traditional individualistic and information processing approach......The Kaleidoscope1 Jointly Executed Integrating Research Project (JEIRP) on Conditions for Productive Networked Learning Environments is developing and elaborating conceptual understandings of Computer Supported Collaborative Learning (CSCL) emphasizing the use of cross-cultural comparative......: Pedagogical design and the dialectics of the digital artefacts, the concept of collaboration, ethics/trust, identity and the role of scaffolding of networked learning environments.   The JEIRP is motivated by the fact that many networked learning environments in various European educational settings...

Learning Networks for Professional Development & Lifelong Learning

NARCIS (Netherlands)

Brouns, Francis; Sloep, Peter

2009-01-01

Brouns, F., & Sloep, P. B. (2009). Learning Networks for Professional Development & Lifelong Learning. Presentation of the Learning Network Programme for a Korean delegation of Chonnam National University and Dankook University (researchers dr. Jeeheon Ryu and dr. Minjeong Kim and a Group of PhD and

Network Learning and Innovation in SME Formal Networks

Directory of Open Access Journals (Sweden)

Jivka Deiters

2013-02-01

Full Text Available The driver for this paper is the need to better understand the potential for learning and innovation that networks canprovide especially for small and medium sized enterprises (SMEs which comprise by far the majority of enterprises in the food sector. With the challenges the food sector is facing in the near future, learning and innovation or more focused, as it is being discussed in the paper, ‘learning for innovation’ are not just opportunities but pre‐conditions for the sustainability of the sector. Network initiatives that could provide appropriate support involve social interaction and knowledge exchange, learning, competence development, and coordination (organization and management of implementation. The analysis identifies case studies in any of these orientations which serve different stages of the innovation process: invention and implementation. The variety of network case studies cover networks linked to a focus group for training, research, orconsulting, networks dealing with focused market oriented product or process development, promotional networks, and networks for open exchange and social networking.

Optimal neural networks for protein-structure prediction

International Nuclear Information System (INIS)

Head-Gordon, T.; Stillinger, F.H.

1993-01-01

The successful application of neural-network algorithms for prediction of protein structure is stymied by three problem areas: the sparsity of the database of known protein structures, poorly devised network architectures which make the input-output mapping opaque, and a global optimization problem in the multiple-minima space of the network variables. We present a simplified polypeptide model residing in two dimensions with only two amino-acid types, A and B, which allows the determination of the global energy structure for all possible sequences of pentamer, hexamer, and heptamer lengths. This model simplicity allows us to compile a complete structural database and to devise neural networks that reproduce the tertiary structure of all sequences with absolute accuracy and with the smallest number of network variables. These optimal networks reveal that the three problem areas are convoluted, but that thoughtful network designs can actually deconvolute these detrimental traits to provide network algorithms that genuinely impact on the ability of the network to generalize or learn the desired mappings. Furthermore, the two-dimensional polypeptide model shows sufficient chemical complexity so that transfer of neural-network technology to more realistic three-dimensional proteins is evident

Inference of time-delayed gene regulatory networks based on dynamic Bayesian network hybrid learning method.

Science.gov (United States)

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.

Facilitative Components of Collaborative Learning: A Review of Nine Health Research Networks.

Science.gov (United States)

Leroy, Lisa; Rittner, Jessica Levin; Johnson, Karin E; Gerteis, Jessie; Miller, Therese

2017-02-01

Collaborative research networks are increasingly used as an effective mechanism for accelerating knowledge transfer into policy and practice. This paper explored the characteristics and collaborative learning approaches of nine health research networks. Semi-structured interviews with representatives from eight diverse US health services research networks conducted between November 2012 and January 2013 and program evaluation data from a ninth. The qualitative analysis assessed each network's purpose, duration, funding sources, governance structure, methods used to foster collaboration, and barriers and facilitators to collaborative learning. The authors reviewed detailed notes from the interviews to distill salient themes. Face-to-face meetings, intentional facilitation and communication, shared vision, trust among members and willingness to work together were key facilitators of collaborative learning. Competing priorities for members, limited funding and lack of long-term support and geographic dispersion were the main barriers to coordination and collaboration across research network members. The findings illustrate the importance of collaborative learning in research networks and the challenges to evaluating the success of research network functionality. Conducting readiness assessments and developing process and outcome evaluation metrics will advance the design and show the impact of collaborative research networks. Copyright © 2017 Longwoods Publishing.

Learning, memory, and the role of neural network architecture.

Directory of Open Access Journals (Sweden)

Ann M Hermundstad

2011-06-01

Full Text Available The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

Adaptive competitive learning neural networks

Directory of Open Access Journals (Sweden)

Ahmed R. Abas

2013-11-01

Full Text Available In this paper, the adaptive competitive learning (ACL neural network algorithm is proposed. This neural network not only groups similar input feature vectors together but also determines the appropriate number of groups of these vectors. This algorithm uses a new proposed criterion referred to as the ACL criterion. This criterion evaluates different clustering structures produced by the ACL neural network for an input data set. Then, it selects the best clustering structure and the corresponding network architecture for this data set. The selected structure is composed of the minimum number of clusters that are compact and balanced in their sizes. The selected network architecture is efficient, in terms of its complexity, as it contains the minimum number of neurons. Synaptic weight vectors of these neurons represent well-separated, compact and balanced clusters in the input data set. The performance of the ACL algorithm is evaluated and compared with the performance of a recently proposed algorithm in the literature in clustering an input data set and determining its number of clusters. Results show that the ACL algorithm is more accurate and robust in both determining the number of clusters and allocating input feature vectors into these clusters than the other algorithm especially with data sets that are sparsely distributed.

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

Learning Orthographic Structure with Sequential Generative Neural Networks

Science.gov (United States)

Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

2016-01-01

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in…

NCI National Clinical Trials Network Structure

Science.gov (United States)

Learn about how the National Clinical Trials Network (NCTN) is structured. The NCTN is a program of the National Cancer Institute that gives funds and other support to cancer research organizations to conduct cancer clinical trials.

Networked Learning and Network Science: Potential Applications to Health Professionals' Continuing Education and Development.

Science.gov (United States)

Margolis, Alvaro; Parboosingh, John

2015-01-01

Prior interpersonal relationships and interactivity among members of professional associations may impact the learning process in continuing medical education (CME). On the other hand, CME programs that encourage interactivity between participants may impact structures and behaviors in these professional associations. With the advent of information and communication technologies, new communication spaces have emerged that have the potential to enhance networked learning in national and international professional associations and increase the effectiveness of CME for health professionals. In this article, network science, based on the application of network theory and other theories, is proposed as an approach to better understand the contribution networking and interactivity between health professionals in professional communities make to their learning and adoption of new practices over time. © 2015 The Alliance for Continuing Education in the Health Professions, the Society for Academic Continuing Medical Education, and the Council on Continuing Medical Education, Association for Hospital Medical Education.

On structure-exploiting trust-region regularized nonlinear least squares algorithms for neural-network learning.

Science.gov (United States)

Mizutani, Eiji; Demmel, James W

2003-01-01

This paper briefly introduces our numerical linear algebra approaches for solving structured nonlinear least squares problems arising from 'multiple-output' neural-network (NN) models. Our algorithms feature trust-region regularization, and exploit sparsity of either the 'block-angular' residual Jacobian matrix or the 'block-arrow' Gauss-Newton Hessian (or Fisher information matrix in statistical sense) depending on problem scale so as to render a large class of NN-learning algorithms 'efficient' in both memory and operation costs. Using a relatively large real-world nonlinear regression application, we shall explain algorithmic strengths and weaknesses, analyzing simulation results obtained by both direct and iterative trust-region algorithms with two distinct NN models: 'multilayer perceptrons' (MLP) and 'complementary mixtures of MLP-experts' (or neuro-fuzzy modular networks).

Adapting Bayes Network Structures to Non-stationary Domains

DEFF Research Database (Denmark)

Nielsen, Søren Holbech; Nielsen, Thomas Dyhre

2008-01-01

When an incremental structural learning method gradually modifies a Bayesian network (BN) structure to fit a sequential stream of observations, we call the process structural adaptation. Structural adaptation is useful when the learner is set to work in an unknown environment, where a BN is gradu...

Using Social Networks to Enhance Teaching and Learning Experiences in Higher Learning Institutions

Science.gov (United States)

Balakrishnan, Vimala

2014-01-01

The paper first explores the factors that affect the use of social networks to enhance teaching and learning experiences among students and lecturers, using structured questionnaires prepared based on the Push-Pull-Mooring framework. A total of 455 students and lecturers from higher learning institutions in Malaysia participated in this study.…

How to Trigger Emergence and Self-Organisation in Learning Networks

Science.gov (United States)

Brouns, Francis; Fetter, Sibren; van Rosmalen, Peter

The previous chapters of this section discussed why the social structure of Learning Networks is important and present guidelines on how to maintain and allow the emergence of communities in Learning Networks. Chapter 2 explains how Learning Networks rely on social interaction and active participations of the participants. Chapter 3 then continues by presenting guidelines and policies that should be incorporated into Learning Network Services in order to maintain existing communities by creating conditions that promote social interaction and knowledge sharing. Chapter 4 discusses the necessary conditions required for knowledge sharing to occur and to trigger communities to self-organise and emerge. As pointed out in Chap. 4, ad-hoc transient communities facilitate the emergence of social interaction in Learning Networks, self-organising them into communities, taking into account personal characteristics, community characteristics and general guidelines. As explained in Chap. 4 community members would benefit from a service that brings suitable people together for a specific purpose, because it will allow the participant to focus on the knowledge sharing process by reducing the effort or costs. In the current chapter, we describe an example of a peer support Learning Network Service based on the mechanism of peer tutoring in ad-hoc transient communities.

Neural networks and statistical learning

CERN Document Server

Du, Ke-Lin

2014-01-01

Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...

What Online Networks Offer: "Online Network Compositions and Online Learning Experiences of Three Ethnic Groups"

Science.gov (United States)

Lecluijze, Suzanne Elisabeth; de Haan, Mariëtte; Ünlüsoy, Asli

2015-01-01

This exploratory study examines ethno-cultural diversity in youth's narratives regarding their "online" learning experiences while also investigating how these narratives can be understood from the analysis of their online network structure and composition. Based on ego-network data of 79 respondents this study compared the…

Blending Formal and Informal Learning Networks for Online Learning

Science.gov (United States)

Czerkawski, Betül C.

2016-01-01

With the emergence of social software and the advance of web-based technologies, online learning networks provide invaluable opportunities for learning, whether formal or informal. Unlike top-down, instructor-centered, and carefully planned formal learning settings, informal learning networks offer more bottom-up, student-centered participatory…

Networked professional learning

NARCIS (Netherlands)

Sloep, Peter

2013-01-01

Sloep, P. B. (2013). Networked professional learning. In A. Littlejohn, & A. Margaryan (Eds.), Technology-enhanced Professional Learning: Processes, Practices and Tools (pp. 97–108). London: Routledge.

Structural Conditions for Collaboration and Learning in Innovation Networks: Using an Innovation System Performance Lens to Analyse Agricultural Knowledge Systems

NARCIS (Netherlands)

Hermans, F.; Klerkx, L.W.A.; Roep, D.

2015-01-01

Purpose: We investigate how the structural conditions of eight different European agricultural innovation systems can facilitate or hinder collaboration and social learning in multidisciplinary innovation networks. Methodology: We have adapted the Innovation System Failure Matrix to investigate the

Influence of Learning Styles on Social Structures in Online Learning Environments

Science.gov (United States)

Cela, Karina; Sicilia, Miguel-Ángel; Sánchez-Alonso, Salvador

2016-01-01

In e-learning settings, the interactions of students with one another, with the course content and with the instructors generate a considerable amount of information that may be useful for understanding how people learn online. The objective of the present research was to use social network analysis to explore the social structure of an e-learning…

Online Learning of Genetic Network Programming and its Application to Prisoner’s Dilemma Game

Science.gov (United States)

Mabu, Shingo; Hirasawa, Kotaro; Hu, Jinglu; Murata, Junichi

A new evolutionary model with the network structure named Genetic Network Programming (GNP) has been proposed recently. GNP, that is, an expansion of GA and GP, represents solutions as a network structure and evolves it by using “offline learning (selection, mutation, crossover)”. GNP can memorize the past action sequences in the network flow, so it can deal with Partially Observable Markov Decision Process (POMDP) well. In this paper, in order to improve the ability of GNP, Q learning (an off-policy TD control algorithm) that is one of the famous online methods is introduced for online learning of GNP. Q learning is suitable for GNP because (1) in reinforcement learning, the rewards an agent will get in the future can be estimated, (2) TD control doesn’t need much memory and can learn quickly, and (3) off-policy is suitable in order to search for an optimal solution independently of the policy. Finally, in the simulations, online learning of GNP is applied to a player for “Prisoner’s dilemma game” and its ability for online adaptation is confirmed.

A Self-Organizing Incremental Neural Network based on local distribution learning.

Science.gov (United States)

Xing, Youlu; Shi, Xiaofeng; Shen, Furao; Zhou, Ke; Zhao, Jinxi

2016-12-01

In this paper, we propose an unsupervised incremental learning neural network based on local distribution learning, which is called Local Distribution Self-Organizing Incremental Neural Network (LD-SOINN). The LD-SOINN combines the advantages of incremental learning and matrix learning. It can automatically discover suitable nodes to fit the learning data in an incremental way without a priori knowledge such as the structure of the network. The nodes of the network store rich local information regarding the learning data. The adaptive vigilance parameter guarantees that LD-SOINN is able to add new nodes for new knowledge automatically and the number of nodes will not grow unlimitedly. While the learning process continues, nodes that are close to each other and have similar principal components are merged to obtain a concise local representation, which we call a relaxation data representation. A denoising process based on density is designed to reduce the influence of noise. Experiments show that the LD-SOINN performs well on both artificial and real-word data. Copyright © 2016 Elsevier Ltd. All rights reserved.

Impact of censoring on learning Bayesian networks in survival modelling.

Science.gov (United States)

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

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

Equilibrium point control of a monkey arm simulator by a fast learning tree structured artificial neural network.

Science.gov (United States)

Dornay, M; Sanger, T D

1993-01-01

A planar 17 muscle model of the monkey's arm based on realistic biomechanical measurements was simulated on a Symbolics Lisp Machine. The simulator implements the equilibrium point hypothesis for the control of arm movements. Given initial and final desired positions, it generates a minimum-jerk desired trajectory of the hand and uses the backdriving algorithm to determine an appropriate sequence of motor commands to the muscles (Flash 1987; Mussa-Ivaldi et al. 1991; Dornay 1991b). These motor commands specify a temporal sequence of stable (attractive) equilibrium positions which lead to the desired hand movement. A strong disadvantage of the simulator is that it has no memory of previous computations. Determining the desired trajectory using the minimum-jerk model is instantaneous, but the laborious backdriving algorithm is slow, and can take up to one hour for some trajectories. The complexity of the required computations makes it a poor model for biological motor control. We propose a computationally simpler and more biologically plausible method for control which achieves the benefits of the backdriving algorithm. A fast learning, tree-structured network (Sanger 1991c) was trained to remember the knowledge obtained by the backdriving algorithm. The neural network learned the nonlinear mapping from a 2-dimensional cartesian planar hand position (x,y) to a 17-dimensional motor command space (u1, . . ., u17). Learning 20 training trajectories, each composed of 26 sample points [[x,y], [u1, . . ., u17] took only 20 min on a Sun-4 Sparc workstation. After the learning stage, new, untrained test trajectories as well as the original trajectories of the hand were given to the neural network as input. The network calculated the required motor commands for these movements. The resulting movements were close to the desired ones for both the training and test cases.

Social Interaction in Learning Networks

NARCIS (Netherlands)

Sloep, Peter

2009-01-01

The original publication is available from www.springerlink.com. Sloep, P. (2009). Social Interaction in Learning Networks. In R. Koper (Ed.), Learning Network Services for Professional Development (pp 13-15). Berlin, Germany: Springer Verlag.

The overlapping community structure of structural brain network in young healthy individuals.

Directory of Open Access Journals (Sweden)

Kai Wu

2011-05-01

Full Text Available Community structure is a universal and significant feature of many complex networks in biology, society, and economics. Community structure has also been revealed in human brain structural and functional networks in previous studies. However, communities overlap and share many edges and nodes. Uncovering the overlapping community structure of complex networks remains largely unknown in human brain networks. Here, using regional gray matter volume, we investigated the structural brain network among 90 brain regions (according to a predefined anatomical atlas in 462 young, healthy individuals. Overlapped nodes between communities were defined by assuming that nodes (brain regions can belong to more than one community. We demonstrated that 90 brain regions were organized into 5 overlapping communities associated with several well-known brain systems, such as the auditory/language, visuospatial, emotion, decision-making, social, control of action, memory/learning, and visual systems. The overlapped nodes were mostly involved in an inferior-posterior pattern and were primarily related to auditory and visual perception. The overlapped nodes were mainly attributed to brain regions with higher node degrees and nodal efficiency and played a pivotal role in the flow of information through the structural brain network. Our results revealed fuzzy boundaries between communities by identifying overlapped nodes and provided new insights into the understanding of the relationship between the structure and function of the human brain. This study provides the first report of the overlapping community structure of the structural network of the human brain.

New designing of E-Learning systems with using network learning

OpenAIRE

Malayeri, Amin Daneshmand; Abdollahi, Jalal

2010-01-01

One of the most applied learning in virtual spaces is using E-Learning systems. Some E-Learning methodologies has been introduced, but the main subject is the most positive feedback from E-Learning systems. In this paper, we introduce a new methodology of E-Learning systems entitle "Network Learning" with review of another aspects of E-Learning systems. Also, we present benefits and advantages of using these systems in educating and fast learning programs. Network Learning can be programmable...

Developing student engagement in networked teaching and learning practices through problem- and project-based learning approaches

DEFF Research Database (Denmark)

Andreasen, Lars Birch; Lerche Nielsen, Jørgen

2012-01-01

This paper focuses on how learner engagement can be facilitated through use of social media and communication technologies. The discussions are based on the Danish Master’s Programme of ICT and Learning (MIL), where students study in groups within a networked learning structure. The paper reflect...

Overcoming uncertainty for within-network relational machine learning

OpenAIRE

Pfeiffer, Joseph J.

2015-01-01

People increasingly communicate through email and social networks to maintain friendships and conduct business, as well as share online content such as pictures, videos and products. Relational machine learning (RML) utilizes a set of observed attributes and network structure to predict corresponding labels for items; for example, to predict individuals engaged in securities fraud, we can utilize phone calls and workplace information to make joint predictions over the individuals. However, in...

Disentangling bipartite and core-periphery structure in financial networks

International Nuclear Information System (INIS)

Barucca, Paolo; Lillo, Fabrizio

2016-01-01

A growing number of systems are represented as networks whose architecture conveys significant information and determines many of their properties. Examples of network architecture include modular, bipartite, and core-periphery structures. However inferring the network structure is a non trivial task and can depend sometimes on the chosen null model. Here we propose a method for classifying network structures and ranking its nodes in a statistically well-grounded fashion. The method is based on the use of Belief Propagation for learning through Entropy Maximization on both the Stochastic Block Model (SBM) and the degree-corrected Stochastic Block Model (dcSBM). As a specific application we show how the combined use of the two ensembles—SBM and dcSBM—allows to disentangle the bipartite and the core-periphery structure in the case of the e-MID interbank network. Specifically we find that, taking into account the degree, this interbank network is better described by a bipartite structure, while using the SBM the core-periphery structure emerges only when data are aggregated for more than a week.

Structure Learning and Statistical Estimation in Distribution Networks - Part II

Energy Technology Data Exchange (ETDEWEB)

Deka, Deepjyoti [Univ. of Texas, Austin, TX (United States); Backhaus, Scott N. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Chertkov, Michael [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

2015-02-13

Limited placement of real-time monitoring devices in the distribution grid, recent trends notwithstanding, has prevented the easy implementation of demand-response and other smart grid applications. Part I of this paper discusses the problem of learning the operational structure of the grid from nodal voltage measurements. In this work (Part II), the learning of the operational radial structure is coupled with the problem of estimating nodal consumption statistics and inferring the line parameters in the grid. Based on a Linear-Coupled(LC) approximation of AC power flows equations, polynomial time algorithms are designed to identify the structure and estimate nodal load characteristics and/or line parameters in the grid using the available nodal voltage measurements. Then the structure learning algorithm is extended to cases with missing data, where available observations are limited to a fraction of the grid nodes. The efficacy of the presented algorithms are demonstrated through simulations on several distribution test cases.

Structural network heterogeneities and network dynamics: a possible dynamical mechanism for hippocampal memory reactivation.

Science.gov (United States)

Jablonski, Piotr; Poe, Gina; Zochowski, Michal

2007-03-01

The hippocampus has the capacity for reactivating recently acquired memories and it is hypothesized that one of the functions of sleep reactivation is the facilitation of consolidation of novel memory traces. The dynamic and network processes underlying such a reactivation remain, however, unknown. We show that such a reactivation characterized by local, self-sustained activity of a network region may be an inherent property of the recurrent excitatory-inhibitory network with a heterogeneous structure. The entry into the reactivation phase is mediated through a physiologically feasible regulation of global excitability and external input sources, while the reactivated component of the network is formed through induced network heterogeneities during learning. We show that structural changes needed for robust reactivation of a given network region are well within known physiological parameters.

Reconstructing Causal Biological Networks through Active Learning.

Directory of Open Access Journals (Sweden)

Hyunghoon Cho

Full Text Available Reverse-engineering of biological networks is a central problem in systems biology. The use of intervention data, such as gene knockouts or knockdowns, is typically used for teasing apart causal relationships among genes. Under time or resource constraints, one needs to carefully choose which intervention experiments to carry out. Previous approaches for selecting most informative interventions have largely been focused on discrete Bayesian networks. However, continuous Bayesian networks are of great practical interest, especially in the study of complex biological systems and their quantitative properties. In this work, we present an efficient, information-theoretic active learning algorithm for Gaussian Bayesian networks (GBNs, which serve as important models for gene regulatory networks. In addition to providing linear-algebraic insights unique to GBNs, leading to significant runtime improvements, we demonstrate the effectiveness of our method on data simulated with GBNs and the DREAM4 network inference challenge data sets. Our method generally leads to faster recovery of underlying network structure and faster convergence to final distribution of confidence scores over candidate graph structures using the full data, in comparison to random selection of intervention experiments.

Structuring and Regulating Collaborative Learning in Higher Education with Wireless Networks and Mobile Tools

Science.gov (United States)

Jarvela, Sanna; Naykki, Piia; Laru, Jari; Luokkanen, Tiina

2007-01-01

In our recent research we have explored possibilities to scaffold collaborative learning in higher education with wireless networks and mobile tools. The pedagogical ideas are grounded on concepts of collaborative learning, including the socially shared origin of cognition, as well as self-regulated learning theory. This paper presents our three…

System level mechanisms of adaptation, learning, memory formation and evolvability: the role of chaperone and other networks.

Science.gov (United States)

Gyurko, David M; Soti, Csaba; Stetak, Attila; Csermely, Peter

2014-05-01

During the last decade, network approaches became a powerful tool to describe protein structure and dynamics. Here, we describe first the protein structure networks of molecular chaperones, then characterize chaperone containing sub-networks of interactomes called as chaperone-networks or chaperomes. We review the role of molecular chaperones in short-term adaptation of cellular networks in response to stress, and in long-term adaptation discussing their putative functions in the regulation of evolvability. We provide a general overview of possible network mechanisms of adaptation, learning and memory formation. We propose that changes of network rigidity play a key role in learning and memory formation processes. Flexible network topology provides ' learning-competent' state. Here, networks may have much less modular boundaries than locally rigid, highly modular networks, where the learnt information has already been consolidated in a memory formation process. Since modular boundaries are efficient filters of information, in the 'learning-competent' state information filtering may be much smaller, than after memory formation. This mechanism restricts high information transfer to the 'learning competent' state. After memory formation, modular boundary-induced segregation and information filtering protect the stored information. The flexible networks of young organisms are generally in a 'learning competent' state. On the contrary, locally rigid networks of old organisms have lost their 'learning competent' state, but store and protect their learnt information efficiently. We anticipate that the above mechanism may operate at the level of both protein-protein interaction and neuronal networks.

Fastest learning in small-world neural networks

International Nuclear Information System (INIS)

Simard, D.; Nadeau, L.; Kroeger, H.

2005-01-01

We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition

Energy consumption analysis for various memristive networks under different learning strategies

Science.gov (United States)

Deng, Lei; Wang, Dong; Zhang, Ziyang; Tang, Pei; Li, Guoqi; Pei, Jing

2016-02-01

Recently, various memristive systems emerge to emulate the efficient computing paradigm of the brain cortex; whereas, how to make them energy efficient still remains unclear, especially from an overall perspective. Here, a systematical and bottom-up energy consumption analysis is demonstrated, including the memristor device level and the network learning level. We propose an energy estimating methodology when modulating the memristive synapses, which is simulated in three typical neural networks with different synaptic structures and learning strategies for both offline and online learning. These results provide an in-depth insight to create energy efficient brain-inspired neuromorphic devices in the future.

Learning Networks for Professional Development & Lifelong Learning

NARCIS (Netherlands)

Sloep, Peter

2009-01-01

Sloep, P. B. (2009). Learning Networks for Professional Development & Lifelong Learning. Presentation at a NeLLL seminar with Etienne Wenger held at the Open Universiteit Nederland. September, 10, 2009, Heerlen, The Netherlands.

Edmodo social learning network for elementary school mathematics learning

Science.gov (United States)

Ariani, Y.; Helsa, Y.; Ahmad, S.; Prahmana, RCI

2017-12-01

A developed instructional media can be as printed media, visual media, audio media, and multimedia. The development of instructional media can also take advantage of technological development by utilizing Edmodo social network. This research aims to develop a digital classroom learning model using Edmodo social learning network for elementary school mathematics learning which is practical, valid and effective in order to improve the quality of learning activities. The result of this research showed that the prototype of mathematics learning device for elementary school students using Edmodo was in good category. There were 72% of students passed the assessment as a result of Edmodo learning. Edmodo has become a promising way to engage students in a collaborative learning process.

Entropy Learning in Neural Network

Directory of Open Access Journals (Sweden)

Geok See Ng

2017-12-01

Full Text Available In this paper, entropy term is used in the learning phase of a neural network.  As learning progresses, more hidden nodes get into saturation.  The early creation of such hidden nodes may impair generalisation.  Hence entropy approach is proposed to dampen the early creation of such nodes.  The entropy learning also helps to increase the importance of relevant nodes while dampening the less important nodes.  At the end of learning, the less important nodes can then be eliminated to reduce the memory requirements of the neural network.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

International Nuclear Information System (INIS)

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin

2015-01-01

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

Energy Technology Data Exchange (ETDEWEB)

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin, E-mail: xmli@cqu.edu.cn [Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education, Chongqing University, Chongqing 400044 (China); College of Automation, Chongqing University, Chongqing 400044 (China)

2015-11-15

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

Incidental and intentional learning of verbal episodic material differentially modifies functional brain networks.

Directory of Open Access Journals (Sweden)

Marie-Therese Kuhnert

Full Text Available Learning- and memory-related processes are thought to result from dynamic interactions in large-scale brain networks that include lateral and mesial structures of the temporal lobes. We investigate the impact of incidental and intentional learning of verbal episodic material on functional brain networks that we derive from scalp-EEG recorded continuously from 33 subjects during a neuropsychological test schedule. Analyzing the networks' global statistical properties we observe that intentional but not incidental learning leads to a significantly increased clustering coefficient, and the average shortest path length remains unaffected. Moreover, network modifications correlate with subsequent recall performance: the more pronounced the modifications of the clustering coefficient, the higher the recall performance. Our findings provide novel insights into the relationship between topological aspects of functional brain networks and higher cognitive functions.

Idea Management: Perspectives from Leadership, Learning, and Network Theory

NARCIS (Netherlands)

D. Deichmann (Dirk)

2012-01-01

textabstractIn this dissertation, we focus on how leadership styles, individual learning behaviors, and social network structures drive or inhibit organizational members to repeatedly generate and develop innovative ideas. Taking the idea management programs of three multinational companies as the

Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

Science.gov (United States)

Witoonchart, Peerajak; Chongstitvatana, Prabhas

2017-08-01

In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

The Hidden Flow Structure and Metric Space of Network Embedding Algorithms Based on Random Walks.

Science.gov (United States)

Gu, Weiwei; Gong, Li; Lou, Xiaodan; Zhang, Jiang

2017-10-13

Network embedding which encodes all vertices in a network as a set of numerical vectors in accordance with it's local and global structures, has drawn widespread attention. Network embedding not only learns significant features of a network, such as the clustering and linking prediction but also learns the latent vector representation of the nodes which provides theoretical support for a variety of applications, such as visualization, link prediction, node classification, and recommendation. As the latest progress of the research, several algorithms based on random walks have been devised. Although those algorithms have drawn much attention for their high scores in learning efficiency and accuracy, there is still a lack of theoretical explanation, and the transparency of those algorithms has been doubted. Here, we propose an approach based on the open-flow network model to reveal the underlying flow structure and its hidden metric space of different random walk strategies on networks. We show that the essence of embedding based on random walks is the latent metric structure defined on the open-flow network. This not only deepens our understanding of random- walk-based embedding algorithms but also helps in finding new potential applications in network embedding.

Distributed Extreme Learning Machine for Nonlinear Learning over Network

Directory of Open Access Journals (Sweden)

Songyan Huang

2015-02-01

Full Text Available Distributed data collection and analysis over a network are ubiquitous, especially over a wireless sensor network (WSN. To our knowledge, the data model used in most of the distributed algorithms is linear. However, in real applications, the linearity of systems is not always guaranteed. In nonlinear cases, the single hidden layer feedforward neural network (SLFN with radial basis function (RBF hidden neurons has the ability to approximate any continuous functions and, thus, may be used as the nonlinear learning system. However, confined by the communication cost, using the distributed version of the conventional algorithms to train the neural network directly is usually prohibited. Fortunately, based on the theorems provided in the extreme learning machine (ELM literature, we only need to compute the output weights of the SLFN. Computing the output weights itself is a linear learning problem, although the input-output mapping of the overall SLFN is still nonlinear. Using the distributed algorithmto cooperatively compute the output weights of the SLFN, we obtain a distributed extreme learning machine (dELM for nonlinear learning in this paper. This dELM is applied to the regression problem and classification problem to demonstrate its effectiveness and advantages.

Language Choice & Global Learning Networks

Directory of Open Access Journals (Sweden)

Dennis Sayers

1995-05-01

Full Text Available How can other languages be used in conjunction with English to further intercultural and multilingual learning when teachers and students participate in computer-based global learning networks? Two portraits are presented of multilingual activities in the Orillas and I*EARN learning networks, and are discussed as examples of the principal modalities of communication employed in networking projects between distant classes. Next, an important historical precedent --the social controversy which accompanied the introduction of telephone technology at the end of the last century-- is examined in terms of its implications for language choice in contemporary classroom telecomputing projects. Finally, recommendations are offered to guide decision making concerning the role of language choice in promoting collaborative critical inquiry.

Learning Networks Distributed Environment

NARCIS (Netherlands)

Martens, Harrie; Vogten, Hubert; Koper, Rob; Tattersall, Colin; Van Rosmalen, Peter; Sloep, Peter; Van Bruggen, Jan; Spoelstra, Howard

2005-01-01

Learning Networks Distributed Environment is a prototype of an architecture that allows the sharing and modification of learning materials through a number of transport protocols. The prototype implements a p2p protcol using JXTA.

Intelligent sensor networks the integration of sensor networks, signal processing and machine learning

CERN Document Server

Hu, Fei

2012-01-01

Although governments worldwide have invested significantly in intelligent sensor network research and applications, few books cover intelligent sensor networks from a machine learning and signal processing perspective. Filling this void, Intelligent Sensor Networks: The Integration of Sensor Networks, Signal Processing and Machine Learning focuses on the close integration of sensing, networking, and smart signal processing via machine learning. Based on the world-class research of award-winning authors, the book provides a firm grounding in the fundamentals of intelligent sensor networks, incl

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 Social Network Analysis of Teaching and Research Collaboration in a Teachers' Virtual Learning Community

Science.gov (United States)

Lin, Xiaofan; Hu, Xiaoyong; Hu, Qintai; Liu, Zhichun

2016-01-01

Analysing the structure of a social network can help us understand the key factors influencing interaction and collaboration in a virtual learning community (VLC). Here, we describe the mechanisms used in social network analysis (SNA) to analyse the social network structure of a VLC for teachers and discuss the relationship between face-to-face…

Energy consumption analysis for various memristive networks under different learning strategies

Energy Technology Data Exchange (ETDEWEB)

Deng, Lei; Wang, Dong [Center for Brain Inspired Computing Research (CBICR), Department of Precision Instrument, Tsinghua University, Beijing 100084 (China); Zhang, Ziyang; Tang, Pei [Optical Memory National Engineering Research Center, Department of Precision Instrument, Tsinghua University, Beijing 100084 (China); Li, Guoqi, E-mail: liguoqi@mail.tsinghua.edu.cn [Center for Brain Inspired Computing Research (CBICR), Department of Precision Instrument, Tsinghua University, Beijing 100084 (China); Pei, Jing, E-mail: peij@mail.tsinghua.edu.cn [Center for Brain Inspired Computing Research (CBICR), Department of Precision Instrument, Tsinghua University, Beijing 100084 (China); Optical Memory National Engineering Research Center, Department of Precision Instrument, Tsinghua University, Beijing 100084 (China)

2016-02-22

Highlights: • Estimation methodology for energy consumed by memristor is established. • Energy comparisons for different learning strategies in various networks are touched. • Less-pulses and low-power-first modulation methods are energy efficient. • Proper decreasing the memristor modulation precision reduces the energy consumption. • Helpful solutions for power improving in memristive systems are proposed. - Abstract: Recently, various memristive systems emerge to emulate the efficient computing paradigm of the brain cortex; whereas, how to make them energy efficient still remains unclear, especially from an overall perspective. Here, a systematical and bottom-up energy consumption analysis is demonstrated, including the memristor device level and the network learning level. We propose an energy estimating methodology when modulating the memristive synapses, which is simulated in three typical neural networks with different synaptic structures and learning strategies for both offline and online learning. These results provide an in-depth insight to create energy efficient brain-inspired neuromorphic devices in the future.

Energy consumption analysis for various memristive networks under different learning strategies

International Nuclear Information System (INIS)

Deng, Lei; Wang, Dong; Zhang, Ziyang; Tang, Pei; Li, Guoqi; Pei, Jing

2016-01-01

Highlights: • Estimation methodology for energy consumed by memristor is established. • Energy comparisons for different learning strategies in various networks are touched. • Less-pulses and low-power-first modulation methods are energy efficient. • Proper decreasing the memristor modulation precision reduces the energy consumption. • Helpful solutions for power improving in memristive systems are proposed. - Abstract: Recently, various memristive systems emerge to emulate the efficient computing paradigm of the brain cortex; whereas, how to make them energy efficient still remains unclear, especially from an overall perspective. Here, a systematical and bottom-up energy consumption analysis is demonstrated, including the memristor device level and the network learning level. We propose an energy estimating methodology when modulating the memristive synapses, which is simulated in three typical neural networks with different synaptic structures and learning strategies for both offline and online learning. These results provide an in-depth insight to create energy efficient brain-inspired neuromorphic devices in the future.

Learning and coding in biological neural networks

Science.gov (United States)

Fiete, Ila Rani

How can large groups of neurons that locally modify their activities learn to collectively perform a desired task? Do studies of learning in small networks tell us anything about learning in the fantastically large collection of neurons that make up a vertebrate brain? What factors do neurons optimize by encoding sensory inputs or motor commands in the way they do? In this thesis I present a collection of four theoretical works: each of the projects was motivated by specific constraints and complexities of biological neural networks, as revealed by experimental studies; together, they aim to partially address some of the central questions of neuroscience posed above. We first study the role of sparse neural activity, as seen in the coding of sequential commands in a premotor area responsible for birdsong. We show that the sparse coding of temporal sequences in the songbird brain can, in a network where the feedforward plastic weights must translate the sparse sequential code into a time-varying muscle code, facilitate learning by minimizing synaptic interference. Next, we propose a biologically plausible synaptic plasticity rule that can perform goal-directed learning in recurrent networks of voltage-based spiking neurons that interact through conductances. Learning is based on the correlation of noisy local activity with a global reward signal; we prove that this rule performs stochastic gradient ascent on the reward. Thus, if the reward signal quantifies network performance on some desired task, the plasticity rule provably drives goal-directed learning in the network. To assess the convergence properties of the learning rule, we compare it with a known example of learning in the brain. Song-learning in finches is a clear example of a learned behavior, with detailed available neurophysiological data. With our learning rule, we train an anatomically accurate model birdsong network that drives a sound source to mimic an actual zebrafinch song. Simulation and

Collective Learning in Games through Social Networks

NARCIS (Netherlands)

Kosterman, S.; Gierasimczuk, N.; Armentano, M.G.; Monteserin, A.; Tang, J.; Yannibelli, V.

2015-01-01

This paper argues that combining social networks communication and games can positively influence the learning behavior of players. We propose a computational model that combines features of social network learning (communication) and game-based learning (strategy reinforcement). The focus is on

Sparse dictionary learning of resting state fMRI networks.

Science.gov (United States)

Eavani, Harini; Filipovych, Roman; Davatzikos, Christos; Satterthwaite, Theodore D; Gur, Raquel E; Gur, Ruben C

2012-07-02

Research in resting state fMRI (rsfMRI) has revealed the presence of stable, anti-correlated functional subnetworks in the brain. Task-positive networks are active during a cognitive process and are anti-correlated with task-negative networks, which are active during rest. In this paper, based on the assumption that the structure of the resting state functional brain connectivity is sparse, we utilize sparse dictionary modeling to identify distinct functional sub-networks. We propose two ways of formulating the sparse functional network learning problem that characterize the underlying functional connectivity from different perspectives. Our results show that the whole-brain functional connectivity can be concisely represented with highly modular, overlapping task-positive/negative pairs of sub-networks.

Supervised Learning with Complex-valued Neural Networks

CERN Document Server

Suresh, Sundaram; Savitha, Ramasamy

2013-01-01

Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks.  Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computati...

Changing Conditions for Networked Learning?

DEFF Research Database (Denmark)

Ryberg, Thomas

2011-01-01

in describing the novel pedagogical potentials of these new technologies and practices (e.g. in debates around virtual learning environments versus personal learning environment). Likewise, I shall briefly discuss the notions of ‘digital natives’ or ‘the net generation’ from a critical perspective...... of social technologies. I argue that we are seeing the emergence of new architectures and scales of participation, collaboration and networking e.g. through interesting formations of learning networks at different levels of scale, for different purposes and often bridging boundaries such as formal...

Learning-parameter adjustment in neural networks

Science.gov (United States)

Heskes, Tom M.; Kappen, Bert

1992-06-01

We present a learning-parameter adjustment algorithm, valid for a large class of learning rules in neural-network literature. The algorithm follows directly from a consideration of the statistics of the weights in the network. The characteristic behavior of the algorithm is calculated, both in a fixed and a changing environment. A simple example, Widrow-Hoff learning for statistical classification, serves as an illustration.

Researching Design, Experience and Practice of Networked Learning

DEFF Research Database (Denmark)

Hodgson, Vivien; de Laat, Maarten; McConnell, David

2014-01-01

and final section draws attention to a growing topic of interest within networked learning: that of networked learning in informal practices. In addition, we provide a reflection on the theories, methods and settings featured in the networked learning research of the chapters. We conclude the introduction...

Learning Bayesian networks for discrete data

KAUST Repository

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.

‘Living' theory: a pedagogical framework for process support in networked learning

Directory of Open Access Journals (Sweden)

Philipa Levy

2006-12-01

Full Text Available This paper focuses on the broad outcome of an action research project in which practical theory was developed in the field of networked learning through case-study analysis of learners' experiences and critical evaluation of educational practice. It begins by briefly discussing the pedagogical approach adopted for the case-study course and the action research methodology. It then identifies key dimensions of four interconnected developmental processes–orientation, communication, socialisation and organisation–that were associated with ‘learning to learn' in the course's networked environment, and offers a flavour of participants' experiences in relation to these processes. A number of key evaluation issues that arose are highlighted. Finally, the paper presents the broad conceptual framework for the design and facilitation of process support in networked learning that was derived from this research. The framework proposes a strong, explicit focus on support for process as well as domain learning, and progression from tighter to looser design and facilitation structures for process-focused (as well as domain-focused learning tasks.

Anatomy and histology as socially networked learning environments: some preliminary findings.

Science.gov (United States)

Hafferty, Frederic W; Castellani, Brian; Hafferty, Philip K; Pawlina, Wojciech

2013-09-01

An exploratory study to better understand the "networked" life of the medical school as a learning environment. In a recent academic year, the authors gathered data during two six-week blocks of a sequential histology and anatomy course at a U.S. medical college. An eight-item questionnaire captured different dimensions of student interactions. The student cohort/network was 48 first-year medical students. Using social network analysis (SNA), the authors focused on (1) the initial structure and the evolution of informal class networks over time, (2) how informal class networks compare to formal in-class small-group assignments in influencing student information gathering, and (3) how peer assignment of professionalism role model status is shaped more by informal than formal ties. In examining these latter two issues, the authors explored not only how formal group assignment persisted over time but also how it functioned to prevent the tendency for groupings based on gender or ethnicity. The study revealed an evolving dynamic between the formal small-group learning structure of the course blocks and the emergence of informal student networks. For example, whereas formal group membership did influence in-class questions and did prevent formation of groups of like gender and ethnicity, outside-class questions and professionalism were influenced more by informal group ties where gender and, to a much lesser extent, ethnicity influence student information gathering. The richness of these preliminary findings suggests that SNA may be a useful tool in examining an array of medical student learning encounters.

Learning network theory : its contribution to our understanding of work-based learning projects and learning climate

NARCIS (Netherlands)

Poell, R.F.; Moorsel, M.A.A.H. van

1996-01-01

This paper discusses the relevance of Van der Krogt's learning network theory (1995) for our understanding of the concepts of work-related learning projects and learning climate in organisations. The main assumptions of the learning network theory are presented and transferred to the level of

Cooperative Learning for Distributed In-Network Traffic Classification

Science.gov (United States)

Joseph, S. B.; Loo, H. R.; Ismail, I.; Andromeda, T.; Marsono, M. N.

2017-04-01

Inspired by the concept of autonomic distributed/decentralized network management schemes, we consider the issue of information exchange among distributed network nodes to network performance and promote scalability for in-network monitoring. In this paper, we propose a cooperative learning algorithm for propagation and synchronization of network information among autonomic distributed network nodes for online traffic classification. The results show that network nodes with sharing capability perform better with a higher average accuracy of 89.21% (sharing data) and 88.37% (sharing clusters) compared to 88.06% for nodes without cooperative learning capability. The overall performance indicates that cooperative learning is promising for distributed in-network traffic classification.

Distance learning, problem based learning and dynamic knowledge networks.

Science.gov (United States)

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.

A Team Formation and Project-based Learning Support Service for Social Learning Networks

NARCIS (Netherlands)

Spoelstra, Howard; Van Rosmalen, Peter; Van de Vrie, Evert; Obreza, Matija; Sloep, Peter

2014-01-01

The Internet affords new approaches to learning. Geographically dispersed self-directed learners can learn in computer-supported communities, forming social learning networks. However, self-directed learners can suffer from a lack of continuous motivation. And surprisingly, social learning networks

Contingent factors affecting network learning

OpenAIRE

Peters, Linda D.; Pressey, Andrew D.; Johnston, Wesley J.

2016-01-01

To increase understanding of the impact of individuals on organizational learning processes, this paper explores the impact of individual cognition and action on the absorptive capacity process of the wider network. In particular this study shows how contingent factors such as social integration mechanisms and power relationships influence how network members engage in, and benefit from, learning. The use of cognitive consistency and sensemaking theory enables examination of how these conting...

Learning network theory : its contribution to our understanding of work-based learning projects and learning climate

OpenAIRE

Poell, R.F.; Moorsel, M.A.A.H. van

1996-01-01

This paper discusses the relevance of Van der Krogt's learning network theory (1995) for our understanding of the concepts of work-related learning projects and learning climate in organisations. The main assumptions of the learning network theory are presented and transferred to the level of learning groups in organisations. Four theoretical types of learning projects are distinguished. Four different approaches to the learning climate of work groups are compared to the approach offered by t...

Stochastic Variational Learning in Recurrent Spiking Networks

Directory of Open Access Journals (Sweden)

Danilo eJimenez Rezende

2014-04-01

Full Text Available The ability to learn and perform statistical inference with biologically plausible recurrent network of spiking neurons is an important step towards understanding perception and reasoning. Here we derive and investigate a new learning rule for recurrent spiking networks with hidden neurons, combining principles from variational learning and reinforcement learning. Our network defines a generative model over spike train histories and the derived learning rule has the form of a local Spike Timing Dependent Plasticity rule modulated by global factors (neuromodulators conveying information about ``novelty on a statistically rigorous ground.Simulations show that our model is able to learn bothstationary and non-stationary patterns of spike trains.We also propose one experiment that could potentially be performed with animals in order to test the dynamics of the predicted novelty signal.

Stochastic variational learning in recurrent spiking networks.

Science.gov (United States)

Jimenez Rezende, Danilo; Gerstner, Wulfram

2014-01-01

The ability to learn and perform statistical inference with biologically plausible recurrent networks of spiking neurons is an important step toward understanding perception and reasoning. Here we derive and investigate a new learning rule for recurrent spiking networks with hidden neurons, combining principles from variational learning and reinforcement learning. Our network defines a generative model over spike train histories and the derived learning rule has the form of a local Spike Timing Dependent Plasticity rule modulated by global factors (neuromodulators) conveying information about "novelty" on a statistically rigorous ground. Simulations show that our model is able to learn both stationary and non-stationary patterns of spike trains. We also propose one experiment that could potentially be performed with animals in order to test the dynamics of the predicted novelty signal.

Structure identification in fuzzy inference using reinforcement learning

Science.gov (United States)

Berenji, Hamid R.; Khedkar, Pratap

1993-01-01

In our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.

THE IMPACTS OF SOCIAL NETWORKING SITES IN HIGHER LEARNING

Directory of Open Access Journals (Sweden)

Mohd Ishak Bin Ismail

2016-02-01

Full Text Available Social networking sites, a web-based application have permeated the boundary between personal lives and student lives. Nowadays, students in higher learning used social networking site such as Facebook to facilitate their learning through the academic collaboration which it further enhances students’ social capital. Social networking site has many advantages to improve students’ learning. To date, Facebook is the leading social networking sites at this time which it being widely used by students in higher learning to communicate to each other, to carry out academic collaboration and sharing resources. Learning through social networking sites is based on the social interaction which learning are emphasizing on students, real world resources, active students` participation, diversity of learning resources and the use of digital tools to deliver meaningful learning. Many studies found the positive, neutral and negative impact of social networking sites on academic performance. Thus, this study will determine the relationship between Facebook usage and academic achievement. Also, it will investigate the association of social capital and academic collaboration to Facebook usage.

Neural networks involved in learning lexical-semantic and syntactic information in a second language.

Science.gov (United States)

Mueller, Jutta L; Rueschemeyer, Shirley-Ann; Ono, Kentaro; Sugiura, Motoaki; Sadato, Norihiro; Nakamura, Akinori

2014-01-01

The present study used functional magnetic resonance imaging (fMRI) to investigate the neural correlates of language acquisition in a realistic learning environment. Japanese native speakers were trained in a miniature version of German prior to fMRI scanning. During scanning they listened to (1) familiar sentences, (2) sentences including a novel sentence structure, and (3) sentences containing a novel word while visual context provided referential information. Learning-related decreases of brain activation over time were found in a mainly left-hemispheric network comprising classical frontal and temporal language areas as well as parietal and subcortical regions and were largely overlapping for novel words and the novel sentence structure in initial stages of learning. Differences occurred at later stages of learning during which content-specific activation patterns in prefrontal, parietal and temporal cortices emerged. The results are taken as evidence for a domain-general network supporting the initial stages of language learning which dynamically adapts as learners become proficient.

Structure-based control of complex networks with nonlinear dynamics.

Science.gov (United States)

Zañudo, Jorge Gomez Tejeda; Yang, Gang; Albert, Réka

2017-07-11

What can we learn about controlling a system solely from its underlying network structure? Here we adapt a recently developed framework for control of networks governed by a broad class of nonlinear dynamics that includes the major dynamic models of biological, technological, and social processes. This feedback-based framework provides realizable node overrides that steer a system toward any of its natural long-term dynamic behaviors, regardless of the specific functional forms and system parameters. We use this framework on several real networks, identify the topological characteristics that underlie the predicted node overrides, and compare its predictions to those of structural controllability in control theory. Finally, we demonstrate this framework's applicability in dynamic models of gene regulatory networks and identify nodes whose override is necessary for control in the general case but not in specific model instances.

A hierarchical model for structure learning based on the physiological characteristics of neurons

Institute of Scientific and Technical Information of China (English)

WEI Hui

2007-01-01

Almost all applications of Artificial Neural Networks (ANNs) depend mainly on their memory ability.The characteristics of typical ANN models are fixed connections,with evolved weights,globalized representations,and globalized optimizations,all based on a mathematical approach.This makes those models to be deficient in robustness,efficiency of learning,capacity,anti-jamming between training sets,and correlativity of samples,etc.In this paper,we attempt to address these problems by adopting the characteristics of biological neurons in morphology and signal processing.A hierarchical neural network was designed and realized to implement structure learning and representations based on connected structures.The basic characteristics of this model are localized and random connections,field limitations of neuron fan-in and fan-out,dynamic behavior of neurons,and samples represented through different sub-circuits of neurons specialized into different response patterns.At the end of this paper,some important aspects of error correction,capacity,learning efficiency,and soundness of structural representation are analyzed theoretically.This paper has demonstrated the feasibility and advantages of structure learning and representation.This model can serve as a fundamental element of cognitive systems such as perception and associative memory.Key-words structure learning,representation,associative memory,computational neuroscience

The Use Of Social Networking Sites For Learning In Institutions Of Higher Learning

Directory of Open Access Journals (Sweden)

Mange Gladys Nkatha

2015-08-01

Full Text Available Abstract Institutions of higher learning are facing greater challenges to change and subjected to various transformations in the surrounding environment including technology. These challenge and motivate them to explore new ways to improve their teaching approaches. This study sought to investigate the use of social networking site in institutions of higher learning. To this end two objectives were formulated 1 to investigate the current state of the use of social networking sites by the students 2 investigate how social networking sites can be used to promote authentic learning in institutions of higher learning. The study adopted exploratory approach using descriptive survey design where a sample of 10 67 students were picked from Jomo Kenyatta University of Agriculture and Technology JKUAT main campus. The findings indicate the use of social networking sites is a viable option as the students are not only members of social networking sites but also that majority have access to the requisite technological devices. Additionally recommendations for ensuring authentic learning were presented. The researcher recommends the exploration of the leveraging of the existing social networking sites for learning in conjunction with key stakeholders.

Bayesian Network Webserver: a comprehensive tool for biological network modeling.

Science.gov (United States)

Ziebarth, Jesse D; Bhattacharya, Anindya; Cui, Yan

2013-11-01

The Bayesian Network Webserver (BNW) is a platform for comprehensive network modeling of systems genetics and other biological datasets. It allows users to quickly and seamlessly upload a dataset, learn the structure of the network model that best explains the data and use the model to understand relationships between network variables. Many datasets, including those used to create genetic network models, contain both discrete (e.g. genotype) and continuous (e.g. gene expression traits) variables, and BNW allows for modeling hybrid datasets. Users of BNW can incorporate prior knowledge during structure learning through an easy-to-use structural constraint interface. After structure learning, users are immediately presented with an interactive network model, which can be used to make testable hypotheses about network relationships. BNW, including a downloadable structure learning package, is available at http://compbio.uthsc.edu/BNW. (The BNW interface for adding structural constraints uses HTML5 features that are not supported by current version of Internet Explorer. We suggest using other browsers (e.g. Google Chrome or Mozilla Firefox) when accessing BNW). ycui2@uthsc.edu. Supplementary data are available at Bioinformatics online.

Protein secondary structure prediction using modular reciprocal bidirectional recurrent neural networks.

Science.gov (United States)

Babaei, Sepideh; Geranmayeh, Amir; Seyyedsalehi, Seyyed Ali

2010-12-01

The supervised learning of recurrent neural networks well-suited for prediction of protein secondary structures from the underlying amino acids sequence is studied. Modular reciprocal recurrent neural networks (MRR-NN) are proposed to model the strong correlations between adjacent secondary structure elements. Besides, a multilayer bidirectional recurrent neural network (MBR-NN) is introduced to capture the long-range intramolecular interactions between amino acids in formation of the secondary structure. The final modular prediction system is devised based on the interactive integration of the MRR-NN and the MBR-NN structures to arbitrarily engage the neighboring effects of the secondary structure types concurrent with memorizing the sequential dependencies of amino acids along the protein chain. The advanced combined network augments the percentage accuracy (Q₃) to 79.36% and boosts the segment overlap (SOV) up to 70.09% when tested on the PSIPRED dataset in three-fold cross-validation. Copyright © 2010 Elsevier Ireland Ltd. All rights reserved.

Functional networks inference from rule-based machine learning models.

Science.gov (United States)

Lazzarini, Nicola; Widera, Paweł; Williamson, Stuart; Heer, Rakesh; Krasnogor, Natalio; Bacardit, Jaume

2016-01-01

Functional networks play an important role in the analysis of biological processes and systems. The inference of these networks from high-throughput (-omics) data is an area of intense research. So far, the similarity-based inference paradigm (e.g. gene co-expression) has been the most popular approach. It assumes a functional relationship between genes which are expressed at similar levels across different samples. An alternative to this paradigm is the inference of relationships from the structure of machine learning models. These models are able to capture complex relationships between variables, that often are different/complementary to the similarity-based methods. We propose a protocol to infer functional networks from machine learning models, called FuNeL. It assumes, that genes used together within a rule-based machine learning model to classify the samples, might also be functionally related at a biological level. The protocol is first tested on synthetic datasets and then evaluated on a test suite of 8 real-world datasets related to human cancer. The networks inferred from the real-world data are compared against gene co-expression networks of equal size, generated with 3 different methods. The comparison is performed from two different points of view. We analyse the enriched biological terms in the set of network nodes and the relationships between known disease-associated genes in a context of the network topology. The comparison confirms both the biological relevance and the complementary character of the knowledge captured by the FuNeL networks in relation to similarity-based methods and demonstrates its potential to identify known disease associations as core elements of the network. Finally, using a prostate cancer dataset as a case study, we confirm that the biological knowledge captured by our method is relevant to the disease and consistent with the specialised literature and with an independent dataset not used in the inference process. The

Cooperation-Controlled Learning for Explicit Class Structure in Self-Organizing Maps

Science.gov (United States)

Kamimura, Ryotaro

2014-01-01

We attempt to demonstrate the effectiveness of multiple points of view toward neural networks. By restricting ourselves to two points of view of a neuron, we propose a new type of information-theoretic method called “cooperation-controlled learning.” In this method, individual and collective neurons are distinguished from one another, and we suppose that the characteristics of individual and collective neurons are different. To implement individual and collective neurons, we prepare two networks, namely, cooperative and uncooperative networks. The roles of these networks and the roles of individual and collective neurons are controlled by the cooperation parameter. As the parameter is increased, the role of cooperative networks becomes more important in learning, and the characteristics of collective neurons become more dominant. On the other hand, when the parameter is small, individual neurons play a more important role. We applied the method to the automobile and housing data from the machine learning database and examined whether explicit class boundaries could be obtained. Experimental results showed that cooperation-controlled learning, in particular taking into account information on input units, could be used to produce clearer class structure than conventional self-organizing maps. PMID:25309950

Cooperation-Controlled Learning for Explicit Class Structure in Self-Organizing Maps

Directory of Open Access Journals (Sweden)

Ryotaro Kamimura

2014-01-01

Full Text Available We attempt to demonstrate the effectiveness of multiple points of view toward neural networks. By restricting ourselves to two points of view of a neuron, we propose a new type of information-theoretic method called “cooperation-controlled learning.” In this method, individual and collective neurons are distinguished from one another, and we suppose that the characteristics of individual and collective neurons are different. To implement individual and collective neurons, we prepare two networks, namely, cooperative and uncooperative networks. The roles of these networks and the roles of individual and collective neurons are controlled by the cooperation parameter. As the parameter is increased, the role of cooperative networks becomes more important in learning, and the characteristics of collective neurons become more dominant. On the other hand, when the parameter is small, individual neurons play a more important role. We applied the method to the automobile and housing data from the machine learning database and examined whether explicit class boundaries could be obtained. Experimental results showed that cooperation-controlled learning, in particular taking into account information on input units, could be used to produce clearer class structure than conventional self-organizing maps.

Interconnecting Networks of Practice for Professional Learning

Directory of Open Access Journals (Sweden)

Julie Mackey

2011-03-01

Full Text Available The article explores the complementary connections between communities of practice and the ways in which individuals orchestrate their engagement with others to further their professional learning. It does so by reporting on part of a research project conducted in New Zealand on teachers’ online professional learning in a university graduate diploma program on ICT education. Evolving from social constructivist pedagogy for online professional development, the research describes how teachers create their own networks of practice as they blend online and offline interactions with fellow learners and workplace colleagues. Teachers’ perspectives of their professional learning activities challenge the way universities design formal online learning communities and highlight the potential for networked learning in the zones and intersections between professional practice and study.The article extends the concepts of Lave and Wenger’s (1991 communities of practice social theory of learning by considering the role participants play in determining their engagement and connections in and across boundaries between online learning communities and professional practice. It provides insights into the applicability of connectivist concepts for developing online pedagogies to promote socially networked learning and for emphasising the role of the learner in defining their learning pathways.

Social Learning Network Analysis Model to Identify Learning Patterns Using Ontology Clustering Techniques and Meaningful Learning

Science.gov (United States)

Firdausiah Mansur, Andi Besse; Yusof, Norazah

2013-01-01

Clustering on Social Learning Network still not explored widely, especially when the network focuses on e-learning system. Any conventional methods are not really suitable for the e-learning data. SNA requires content analysis, which involves human intervention and need to be carried out manually. Some of the previous clustering techniques need…

A review of active learning approaches to experimental design for uncovering biological networks

Science.gov (United States)

2017-01-01

Various types of biological knowledge describe networks of interactions among elementary entities. For example, transcriptional regulatory networks consist of interactions among proteins and genes. Current knowledge about the exact structure of such networks is highly incomplete, and laboratory experiments that manipulate the entities involved are conducted to test hypotheses about these networks. In recent years, various automated approaches to experiment selection have been proposed. Many of these approaches can be characterized as active machine learning algorithms. Active learning is an iterative process in which a model is learned from data, hypotheses are generated from the model to propose informative experiments, and the experiments yield new data that is used to update the model. This review describes the various models, experiment selection strategies, validation techniques, and successful applications described in the literature; highlights common themes and notable distinctions among methods; and identifies likely directions of future research and open problems in the area. PMID:28570593

Co-Operative Learning and Development Networks.

Science.gov (United States)

Hodgson, V.; McConnell, D.

1995-01-01

Discusses the theory, nature, and benefits of cooperative learning. Considers the Cooperative Learning and Development Network (CLDN) trial in the JITOL (Just in Time Open Learning) project and examines the relationship between theories about cooperative learning and the reality of a group of professionals participating in a virtual cooperative…

Network structure exploration in networks with node attributes

Science.gov (United States)

Chen, Yi; Wang, Xiaolong; Bu, Junzhao; Tang, Buzhou; Xiang, Xin

2016-05-01

Complex networks provide a powerful way to represent complex systems and have been widely studied during the past several years. One of the most important tasks of network analysis is to detect structures (also called structural regularities) embedded in networks by determining group number and group partition. Most of network structure exploration models only consider network links. However, in real world networks, nodes may have attributes that are useful for network structure exploration. In this paper, we propose a novel Bayesian nonparametric (BNP) model to explore structural regularities in networks with node attributes, called Bayesian nonparametric attribute (BNPA) model. This model does not only take full advantage of both links between nodes and node attributes for group partition via shared hidden variables, but also determine group number automatically via the Bayesian nonparametric theory. Experiments conducted on a number of real and synthetic networks show that our BNPA model is able to automatically explore structural regularities in networks with node attributes and is competitive with other state-of-the-art models.

Networks and learning in game theory

NARCIS (Netherlands)

Kets, W.

2008-01-01

This work concentrates on two topics, networks and game theory, and learning in games. The first part of this thesis looks at network games and the role of incomplete information in such games. It is assumed that players are located on a network and interact with their neighbors in the network.

Structure constrained by metadata in networks of chess players.

Science.gov (United States)

Almeira, Nahuel; Schaigorodsky, Ana L; Perotti, Juan I; Billoni, Orlando V

2017-11-09

Chess is an emblematic sport that stands out because of its age, popularity and complexity. It has served to study human behavior from the perspective of a wide number of disciplines, from cognitive skills such as memory and learning, to aspects like innovation and decision-making. Given that an extensive documentation of chess games played throughout history is available, it is possible to perform detailed and statistically significant studies about this sport. Here we use one of the most extensive chess databases in the world to construct two networks of chess players. One of the networks includes games that were played over-the-board and the other contains games played on the Internet. We study the main topological characteristics of the networks, such as degree distribution and correlations, transitivity and community structure. We complement the structural analysis by incorporating players' level of play as node metadata. Although both networks are topologically different, we show that in both cases players gather in communities according to their expertise and that an emergent rich-club structure, composed by the top-rated players, is also present.

Learning as Issue Framing in Agricultural Innovation Networks

Science.gov (United States)

Tisenkopfs, Talis; Kunda, Ilona; Šumane, Sandra

2014-01-01

Purpose: Networks are increasingly viewed as entities of learning and innovation in agriculture. In this article we explore learning as issue framing in two agricultural innovation networks. Design/methodology/approach: We combine frame analysis and social learning theories to analyse the processes and factors contributing to frame convergence and…

Empirical Models of Social Learning in a Large, Evolving Network.

Directory of Open Access Journals (Sweden)

Ayşe Başar Bener

Full Text Available This paper advances theories of social learning through an empirical examination of how social networks change over time. Social networks are important for learning because they constrain individuals' access to information about the behaviors and cognitions of other people. Using data on a large social network of mobile device users over a one-month time period, we test three hypotheses: 1 attraction homophily causes individuals to form ties on the basis of attribute similarity, 2 aversion homophily causes individuals to delete existing ties on the basis of attribute dissimilarity, and 3 social influence causes individuals to adopt the attributes of others they share direct ties with. Statistical models offer varied degrees of support for all three hypotheses and show that these mechanisms are more complex than assumed in prior work. Although homophily is normally thought of as a process of attraction, people also avoid relationships with others who are different. These mechanisms have distinct effects on network structure. While social influence does help explain behavior, people tend to follow global trends more than they follow their friends.

Learning Bayesian Networks with Incomplete Data by Augmentation

OpenAIRE

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 ...

THE IMPACTS OF SOCIAL NETWORKING SITES IN HIGHER LEARNING

OpenAIRE

Mohd Ishak Bin Ismail; Ruzaini Bin Abdullah Arshah

2016-01-01

Social networking sites, a web-based application have permeated the boundary between personal lives and student lives. Nowadays, students in higher learning used social networking site such as Facebook to facilitate their learning through the academic collaboration which it further enhances students’ social capital. Social networking site has many advantages to improve students’ learning. To date, Facebook is the leading social networking sites at this time which it being widely used by stude...

Deep learning in neural networks: an overview.

Science.gov (United States)

Schmidhuber, Jürgen

2015-01-01

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

Reversal Learning in Humans and Gerbils: Dynamic Control Network Facilitates Learning.

Science.gov (United States)

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

Identifying Gatekeepers in Online Learning Networks

Science.gov (United States)

Gursakal, Necmi; Bozkurt, Aras

2017-01-01

The rise of the networked society has not only changed our perceptions but also the definitions, roles, processes and dynamics of online learning networks. From offline to online worlds, networks are everywhere and gatekeepers are an important entity in these networks. In this context, the purpose of this paper is to explore gatekeeping and…

Design of a Networked Learning Master Environment for Professionals

DEFF Research Database (Denmark)

Dirckinck-Holmfeld, Lone

2010-01-01

The paper is presenting the overall learning design of MIL (Master in ICT and Learning). The learning design is integrating a number of principles: 1. Principles of problem and project based learning 2. Networked learning / learning in communities of practice. The paper will discuss how these pri......The paper is presenting the overall learning design of MIL (Master in ICT and Learning). The learning design is integrating a number of principles: 1. Principles of problem and project based learning 2. Networked learning / learning in communities of practice. The paper will discuss how...

Thermodynamic efficiency of learning a rule in neural networks

Science.gov (United States)

Goldt, Sebastian; Seifert, Udo

2017-11-01

Biological systems have to build models from their sensory input data that allow them to efficiently process previously unseen inputs. Here, we study a neural network learning a binary classification rule for these inputs from examples provided by a teacher. We analyse the ability of the network to apply the rule to new inputs, that is to generalise from past experience. Using stochastic thermodynamics, we show that the thermodynamic costs of the learning process provide an upper bound on the amount of information that the network is able to learn from its teacher for both batch and online learning. This allows us to introduce a thermodynamic efficiency of learning. We analytically compute the dynamics and the efficiency of a noisy neural network performing online learning in the thermodynamic limit. In particular, we analyse three popular learning algorithms, namely Hebbian, Perceptron and AdaTron learning. Our work extends the methods of stochastic thermodynamics to a new type of learning problem and might form a suitable basis for investigating the thermodynamics of decision-making.

Design and FPGA-implementation of multilayer neural networks with on-chip learning

International Nuclear Information System (INIS)

Haggag, S.S.M.Y

2008-01-01

Artificial Neural Networks (ANN) is used in many applications in the industry because of their parallel structure, high speed, and their ability to give easy solution to complicated problems. For example identifying the orange and apple in the sorting machine with neural network is easier than using image processing techniques to do the same thing. There are different software for designing, training, and testing the ANN, but in order to use the ANN in the industry, it should be implemented on hardware outside the computer. Neural networks are artificial systems inspired on the brain's cognitive behavior, which can learn tasks with some degree of complexity, such as signal processing, diagnosis, robotics, image processing, and pattern recognition. Many applications demand a high computing power and the traditional software implementation are not sufficient.This thesis presents design and FPGA implementation of Multilayer Neural Networks with On-chip learning in re-configurable hardware. Hardware implementation of neural network algorithm is very interesting due their high performance and they can easily be made parallel. The architecture proposed herein takes advantage of distinct data paths for the forward and backward propagation stages and a pipelined adaptation of the on- line backpropagation algorithm to significantly improve the performance of the learning phase. The architecture is easily scalable and able to cope with arbitrary network sizes with the same hardware. The implementation is targeted diagnosis of the Research Reactor accidents to avoid the risk of occurrence of a nuclear accident. The proposed designed circuits are implemented using Xilinx FPGA Chip XC40150xv and occupied 73% of Chip CLBs. It achieved 10.8 μs to take decision in the forward propagation compared with current software implemented of RPS which take 24 ms. The results show that the proposed architecture leads to significant speed up comparing to high end software solutions. On

Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene.

Science.gov (United States)

Li, Jun; Mei, Xue; Prokhorov, Danil; Tao, Dacheng

2017-03-01

Hierarchical neural networks have been shown to be effective in learning representative image features and recognizing object classes. However, most existing networks combine the low/middle level cues for classification without accounting for any spatial structures. For applications such as understanding a scene, how the visual cues are spatially distributed in an image becomes essential for successful analysis. This paper extends the framework of deep neural networks by accounting for the structural cues in the visual signals. In particular, two kinds of neural networks have been proposed. First, we develop a multitask deep convolutional network, which simultaneously detects the presence of the target and the geometric attributes (location and orientation) of the target with respect to the region of interest. Second, a recurrent neuron layer is adopted for structured visual detection. The recurrent neurons can deal with the spatial distribution of visible cues belonging to an object whose shape or structure is difficult to explicitly define. Both the networks are demonstrated by the practical task of detecting lane boundaries in traffic scenes. The multitask convolutional neural network provides auxiliary geometric information to help the subsequent modeling of the given lane structures. The recurrent neural network automatically detects lane boundaries, including those areas containing no marks, without any explicit prior knowledge or secondary modeling.

A Co-Citation Network of Young Children's Learning with Technology

Science.gov (United States)

Tang, Kai-Yu; Li, Ming-Chaun; Hsin, Ching-Ting; Tsai, Chin-Chung

2016-01-01

This paper used a novel literature review approach--co-citation network analysis--to illuminate the latent structure of 87 empirical papers in the field of young children's learning with technology (YCLT). Based on the document co-citation analysis, a total of 206 co-citation relationships among the 87 papers were identified and then graphically…

vhv supply networks, problems of network structure

Energy Technology Data Exchange (ETDEWEB)

Raimbault, J

1966-04-01

The present and future power requirements of the Paris area and the structure of the existing networks are discussed. The various limitations that will have to be allowed for to lay down the structure of a regional transmission network leading in the power of the large national transmission network to within the Paris built up area are described. The theoretical solution that has been adopted, and the features of its final achievement, which is planned for about the year 2000, and the intermediate stages are given. The problem of the structure of the National Power Transmission network which is to supply the regional network was studied. To solve this problem, a 730 kV voltage network will have to be introduced.

[Network structures in biological systems].

Science.gov (United States)

Oleskin, A V

2013-01-01

Network structures (networks) that have been extensively studied in the humanities are characterized by cohesion, a lack of a central control unit, and predominantly fractal properties. They are contrasted with structures that contain a single centre (hierarchies) as well as with those whose elements predominantly compete with one another (market-type structures). As far as biological systems are concerned, their network structures can be subdivided into a number of types involving different organizational mechanisms. Network organization is characteristic of various structural levels of biological systems ranging from single cells to integrated societies. These networks can be classified into two main subgroups: (i) flat (leaderless) network structures typical of systems that are composed of uniform elements and represent modular organisms or at least possess manifest integral properties and (ii) three-dimensional, partly hierarchical structures characterized by significant individual and/or intergroup (intercaste) differences between their elements. All network structures include an element that performs structural, protective, and communication-promoting functions. By analogy to cell structures, this element is denoted as the matrix of a network structure. The matrix includes a material and an immaterial component. The material component comprises various structures that belong to the whole structure and not to any of its elements per se. The immaterial (ideal) component of the matrix includes social norms and rules regulating network elements' behavior. These behavioral rules can be described in terms of algorithms. Algorithmization enables modeling the behavior of various network structures, particularly of neuron networks and their artificial analogs.

Teachers’ motives for learning in networks : costs, rewards and community interest

NARCIS (Netherlands)

van den Beemt, A.A.J.; Ketelaar, E.; Diepstraten, I.; de Laat, M.

2018-01-01

Background: This paper discusses teachers’ perspectives on learning networks and their motives for participating in these networks. Although it is widely held that teachers’ learning may be developed through learning networks, not all teachers participate in such networks. Purpose: The theme of

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....

Evolving autonomous learning in cognitive networks.

Science.gov (United States)

Sheneman, Leigh; Hintze, Arend

2017-12-01

There are two common approaches for optimizing the performance of a machine: genetic algorithms and machine learning. A genetic algorithm is applied over many generations whereas machine learning works by applying feedback until the system meets a performance threshold. These methods have been previously combined, particularly in artificial neural networks using an external objective feedback mechanism. We adapt this approach to Markov Brains, which are evolvable networks of probabilistic and deterministic logic gates. Prior to this work MB could only adapt from one generation to the other, so we introduce feedback gates which augment their ability to learn during their lifetime. We show that Markov Brains can incorporate these feedback gates in such a way that they do not rely on an external objective feedback signal, but instead can generate internal feedback that is then used to learn. This results in a more biologically accurate model of the evolution of learning, which will enable us to study the interplay between evolution and learning and could be another step towards autonomously learning machines.

SpikeTemp: An Enhanced Rank-Order-Based Learning Approach for Spiking Neural Networks With Adaptive Structure.

Science.gov (United States)

Wang, Jinling; Belatreche, Ammar; Maguire, Liam P; McGinnity, Thomas Martin

2017-01-01

This paper presents an enhanced rank-order-based learning algorithm, called SpikeTemp, for spiking neural networks (SNNs) with a dynamically adaptive structure. The trained feed-forward SNN consists of two layers of spiking neurons: 1) an encoding layer which temporally encodes real-valued features into spatio-temporal spike patterns and 2) an output layer of dynamically grown neurons which perform spatio-temporal classification. Both Gaussian receptive fields and square cosine population encoding schemes are employed to encode real-valued features into spatio-temporal spike patterns. Unlike the rank-order-based learning approach, SpikeTemp uses the precise times of the incoming spikes for adjusting the synaptic weights such that early spikes result in a large weight change and late spikes lead to a smaller weight change. This removes the need to rank all the incoming spikes and, thus, reduces the computational cost of SpikeTemp. The proposed SpikeTemp algorithm is demonstrated on several benchmark data sets and on an image recognition task. The results show that SpikeTemp can achieve better classification performance and is much faster than the existing rank-order-based learning approach. In addition, the number of output neurons is much smaller when the square cosine encoding scheme is employed. Furthermore, SpikeTemp is benchmarked against a selection of existing machine learning algorithms, and the results demonstrate the ability of SpikeTemp to classify different data sets after just one presentation of the training samples with comparable classification performance.

Self-Learning Power Control in Wireless Sensor Networks.

Science.gov (United States)

Chincoli, Michele; Liotta, Antonio

2018-01-27

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay.

Aging and Network Properties: Stability Over Time and Links with Learning during Working Memory Training

Directory of Open Access Journals (Sweden)

Alexandru D. Iordan

2018-01-01

Full Text Available Growing evidence suggests that healthy aging affects the configuration of large-scale functional brain networks. This includes reducing network modularity and local efficiency. However, the stability of these effects over time and their potential role in learning remain poorly understood. The goal of the present study was to further clarify previously reported age effects on “resting-state” networks, to test their reliability over time, and to assess their relation to subsequent learning during training. Resting-state fMRI data from 23 young (YA and 20 older adults (OA were acquired in 2 sessions 2 weeks apart. Graph-theoretic analyses identified both consistencies in network structure and differences in module composition between YA and OA, suggesting topological changes and less stability of functional network configuration with aging. Brain-wide, OA showed lower modularity and local efficiency compared to YA, consistent with the idea of age-related functional dedifferentiation, and these effects were replicable over time. At the level of individual networks, OA consistently showed greater participation and lower local efficiency and within-network connectivity in the cingulo-opercular network, as well as lower intra-network connectivity in the default-mode network and greater participation of the somato-sensorimotor network, suggesting age-related differential effects at the level of specialized brain modules. Finally, brain-wide network properties showed associations, albeit limited, with learning rates, as assessed with 10 days of computerized working memory training administered after the resting-state sessions, suggesting that baseline network configuration may influence subsequent learning outcomes. Identification of neural mechanisms associated with learning-induced plasticity is important for further clarifying whether and how such changes predict the magnitude and maintenance of training gains, as well as the extent and limits of

Learning Bayesian networks for discrete data

KAUST Repository

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

Discussion Tool Effects on Collaborative Learning and Social Network Structure

Science.gov (United States)

Tomsic, Astrid; Suthers, Daniel D.

2006-01-01

This study investigated the social network structure of booking officers at the Honolulu Police Department and how the introduction of an online discussion tool affected knowledge about operation of a booking module. Baseline data provided evidence for collaboration among officers in the same district using e-mail, telephone and face-to-face media…

QSAR modelling using combined simple competitive learning networks and RBF neural networks.

Science.gov (United States)

Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E

2018-04-01

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.

Elements of learning technologies designing of engineering networks heat

Directory of Open Access Journals (Sweden)

Sidorkina Irina G.

2016-01-01

Full Text Available Modern educational systems function as a medium fast analysis of shared information that defines them as analytical. The purpose of analytical information processing systems: working with distributed data on a global computer networks, mining and processing of semi structured information, knowledge. Existing mathematical and heuristic methods for the automated synthesis of electronic courses and their corresponding algorithms do not allow the full compliance of development realized in the form of adequate criteria for the totality of the properties distributed educational systems within acceptable time limits and characteristic. Therefore, the development of electronic educational applications must be accompanied by a variety of software support intelligent and adaptive functions. In addition, there is no theoretical justification for integrative aspects and their practical applications for intelligent and adaptive systems of designing distance learning courses. Currently, this type of problem may be considered as a potentially promising. The article presents the functionality of the e-learning course on the design engineering of thermal networks, process modeling in engineering networks with the solution of energy efficiency, detection of problem areas; identify the irrational layout of heaters and others.

Multi-modal Social Networks: A MRF Learning Approach

Science.gov (United States)

2016-06-20

Network forensics: random infection vs spreading epidemic , Proceedings of ACM Sigmetrics. 11-JUN-12, London, UK. : , TOTAL: 4 06/09/2016 Received Paper...Multi-modal Social Networks A MRF Learning Approach The work primarily focused on two lines of research. 1. We propose new greedy algorithms...Box 12211 Research Triangle Park, NC 27709-2211 social networks , learning and inference REPORT DOCUMENTATION PAGE 11. SPONSOR/MONITOR’S REPORT

Structure Learning of Linear Bayesian Networks in High-Dimensions

OpenAIRE

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 ...

Novel Machine Learning-Based Techniques for Efficient Resource Allocation in Next Generation Wireless Networks

KAUST Repository

AlQuerm, Ismail A.

2018-02-21

There is a large demand for applications of high data rates in wireless networks. These networks are becoming more complex and challenging to manage due to the heterogeneity of users and applications specifically in sophisticated networks such as the upcoming 5G. Energy efficiency in the future 5G network is one of the essential problems that needs consideration due to the interference and heterogeneity of the network topology. Smart resource allocation, environmental adaptivity, user-awareness and energy efficiency are essential features in the future networks. It is important to support these features at different networks topologies with various applications. Cognitive radio has been found to be the paradigm that is able to satisfy the above requirements. It is a very interdisciplinary topic that incorporates flexible system architectures, machine learning, context awareness and cooperative networking. Mitola’s vision about cognitive radio intended to build context-sensitive smart radios that are able to adapt to the wireless environment conditions while maintaining quality of service support for different applications. Artificial intelligence techniques including heuristics algorithms and machine learning are the shining tools that are employed to serve the new vision of cognitive radio. In addition, these techniques show a potential to be utilized in an efficient resource allocation for the upcoming 5G networks’ structures such as heterogeneous multi-tier 5G networks and heterogeneous cloud radio access networks due to their capability to allocate resources according to real-time data analytics. In this thesis, we study cognitive radio from a system point of view focusing closely on architectures, artificial intelligence techniques that can enable intelligent radio resource allocation and efficient radio parameters reconfiguration. We propose a modular cognitive resource management architecture, which facilitates a development of flexible control for

Searching for realism, structure and agency in Actor Network Theory.

Science.gov (United States)

Elder-Vass, Dave

2008-09-01

Superficially, Actor Network Theory (ANT) and critical realism (CR) are radically opposed research traditions. Written from a realist perspective, this paper asks whether there might be a basis for finding common ground between these two traditions. It looks in turn at the questions of realism, structure, and agency, analysing the differences between the two perspectives and seeking to identify what each might learn from the other. Overall, the paper argues that there is a great deal that realists can learn from actor network theory; yet ANT remains stunted by its lack of a depth ontology. It fails to recognize the significance of mechanisms, and of their dependence on emergence, and thus lacks both dimensions of the depth that is characteristic of critical realism's ontology. This prevents ANT from recognizing the role and powers of social structure; but on the other hand, realists would do well to heed ANT's call for us to trace the connections through which structures are constantly made and remade. A lack of ontological depth also underpins ANT's practice of treating human and non-human actors symmetrically, yet this remains a valuable provocation to sociologists who neglect non-human entities entirely.

Machine Learning Topological Invariants with Neural Networks

Science.gov (United States)

Zhang, Pengfei; Shen, Huitao; Zhai, Hui

2018-02-01

In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural network can predict their topological winding numbers with nearly 100% accuracy, even for Hamiltonians with larger winding numbers that are not included in the training data. These results show a remarkable success that the neural network can capture the global and nonlinear topological features of quantum phases from local inputs. By opening up the neural network, we confirm that the network does learn the discrete version of the winding number formula. We also make a couple of remarks regarding the role of the symmetry and the opposite effect of regularization techniques when applying machine learning to physical systems.

Bayesian network learning for natural hazard assessments

Science.gov (United States)

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

Functionality for learning networks: lessons learned from social web applications

NARCIS (Netherlands)

Berlanga, Adriana; Sloep, Peter; Brouns, Francis; Van Rosmalen, Peter; Bitter-Rijpkema, Marlies; Koper, Rob

2007-01-01

Berlanga, A. J., Sloep, P., Brouns, F., Van Rosmalen, P., Bitter-Rijpkema, M., & Koper, R. (2007). Functionality for learning networks: lessons learned from social web applications. Proceedings of the ePortfolio 2007 Conference. October, 18-19, 2007, Maastricht, The Netherlands. [See also

On-line learning in radial basis functions networks

OpenAIRE

Freeman, Jason; Saad, David

1997-01-01

An analytic investigation of the average case learning and generalization properties of Radial Basis Function Networks (RBFs) is presented, utilising on-line gradient descent as the learning rule. The analytic method employed allows both the calculation of generalization error and the examination of the internal dynamics of the network. The generalization error and internal dynamics are then used to examine the role of the learning rate and the specialization of the hidden units, which gives ...

Computational modeling of spiking neural network with learning rules from STDP and intrinsic plasticity

Science.gov (United States)

Li, Xiumin; Wang, Wei; Xue, Fangzheng; Song, Yongduan

2018-02-01

Recently there has been continuously increasing interest in building up computational models of spiking neural networks (SNN), such as the Liquid State Machine (LSM). The biologically inspired self-organized neural networks with neural plasticity can enhance the capability of computational performance, with the characteristic features of dynamical memory and recurrent connection cycles which distinguish them from the more widely used feedforward neural networks. Despite a variety of computational models for brain-like learning and information processing have been proposed, the modeling of self-organized neural networks with multi-neural plasticity is still an important open challenge. The main difficulties lie in the interplay among different forms of neural plasticity rules and understanding how structures and dynamics of neural networks shape the computational performance. In this paper, we propose a novel approach to develop the models of LSM with a biologically inspired self-organizing network based on two neural plasticity learning rules. The connectivity among excitatory neurons is adapted by spike-timing-dependent plasticity (STDP) learning; meanwhile, the degrees of neuronal excitability are regulated to maintain a moderate average activity level by another learning rule: intrinsic plasticity (IP). Our study shows that LSM with STDP+IP performs better than LSM with a random SNN or SNN obtained by STDP alone. The noticeable improvement with the proposed method is due to the better reflected competition among different neurons in the developed SNN model, as well as the more effectively encoded and processed relevant dynamic information with its learning and self-organizing mechanism. This result gives insights to the optimization of computational models of spiking neural networks with neural plasticity.

Approximation methods for efficient learning of Bayesian networks

CERN Document Server

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.

Adaptive Learning in Weighted Network Games

NARCIS (Netherlands)

Bayer, Péter; Herings, P. Jean-Jacques; Peeters, Ronald; Thuijsman, Frank

2017-01-01

This paper studies adaptive learning in the class of weighted network games. This class of games includes applications like research and development within interlinked firms, crime within social networks, the economics of pollution, and defense expenditures within allied nations. We show that for

Airport Flight Departure Delay Model on Improved BN Structure Learning

Science.gov (United States)

Cao, Weidong; Fang, Xiangnong

An high score prior genetic simulated annealing Bayesian network structure learning algorithm (HSPGSA) by combining genetic algorithm(GA) with simulated annealing algorithm(SAA) is developed. The new algorithm provides not only with strong global search capability of GA, but also with strong local hill climb search capability of SAA. The structure with the highest score is prior selected. In the mean time, structures with lower score are also could be choice. It can avoid efficiently prematurity problem by higher score individual wrong direct growing population. Algorithm is applied to flight departure delays analysis in a large hub airport. Based on the flight data a BN model is created. Experiments show that parameters learning can reflect departure delay.

Learning by stimulation avoidance: A principle to control spiking neural networks dynamics.

Science.gov (United States)

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.

Networks of Learning

Science.gov (United States)

Bettencourt, Luis; Kaiser, David

2004-03-01

Based on an a historically documented example of scientific discovery - Feynman diagrams as the main calculational tool of theoretical high energy Physics - we map the time evolution of the social network of early adopters through in the US, UK, Japan and the USSR. The spread of the technique for total number of users in each region is then modelled in terms of epidemic models, highlighting parallel and divergent aspects of this analogy. We also show that transient social arrangements develop as the idea is introduced and learned, which later disappear as the technique becomes common knowledge. Such early transient is characterized by abnormally low connectivity distribution powers and by high clustering. This interesting early non-equilibrium stage of network evolution is captured by a new dynamical model for network evolution, which coincides in its long time limit with familiar preferential aggregation dynamics.

Do learning collaboratives strengthen communication? A comparison of organizational team communication networks over time.

Science.gov (United States)

Bunger, Alicia C; Lengnick-Hall, Rebecca

Collaborative learning models were designed to support quality improvements, such as innovation implementation by promoting communication within organizational teams. Yet the effect of collaborative learning approaches on organizational team communication during implementation is untested. The aim of this study was to explore change in communication patterns within teams from children's mental health organizations during a year-long learning collaborative focused on implementing a new treatment. We adopt a social network perspective to examine intraorganizational communication within each team and assess change in (a) the frequency of communication among team members, (b) communication across organizational hierarchies, and (c) the overall structure of team communication networks. A pretest-posttest design compared communication among 135 participants from 21 organizational teams at the start and end of a learning collaborative. At both time points, participants were asked to list the members of their team and rate the frequency of communication with each along a 7-point Likert scale. Several individual, pair-wise, and team level communication network metrics were calculated and compared over time. At the individual level, participants reported communicating with more team members by the end of the learning collaborative. Cross-hierarchical communication did not change. At the team level, these changes manifested differently depending on team size. In large teams, communication frequency increased, and networks grew denser and slightly less centralized. In small teams, communication frequency declined, growing more sparse and centralized. Results suggest that team communication patterns change minimally but evolve differently depending on size. Learning collaboratives may be more helpful for enhancing communication among larger teams; thus, managers might consider selecting and sending larger staff teams to learning collaboratives. This study highlights key future

Biologically-inspired Learning in Pulsed Neural Networks

DEFF Research Database (Denmark)

Lehmann, Torsten; Woodburn, Robin

1999-01-01

Self-learning chips to implement many popular ANN (artificial neural network) algorithms are very difficult to design. We explain why this is so and say what lessons previous work teaches us in the design of self-learning systems. We offer a contribution to the `biologically-inspired' approach......, explaining what we mean by this term and providing an example of a robust, self-learning design that can solve simple classical-conditioning tasks. We give details of the design of individual circuits to perform component functions, which can then be combined into a network to solve the task. We argue...

Learning oncogenetic networks by reducing to mixed integer linear programming.

Science.gov (United States)

Shahrabi Farahani, Hossein; Lagergren, Jens

2013-01-01

Cancer can be a result of accumulation of different types of genetic mutations such as copy number aberrations. The data from tumors are cross-sectional and do not contain the temporal order of the genetic events. Finding the order in which the genetic events have occurred and progression pathways are of vital importance in understanding the disease. In order to model cancer progression, we propose Progression Networks, a special case of Bayesian networks, that are tailored to model disease progression. Progression networks have similarities with Conjunctive Bayesian Networks (CBNs) [1],a variation of Bayesian networks also proposed for modeling disease progression. We also describe a learning algorithm for learning Bayesian networks in general and progression networks in particular. We reduce the hard problem of learning the Bayesian and progression networks to Mixed Integer Linear Programming (MILP). MILP is a Non-deterministic Polynomial-time complete (NP-complete) problem for which very good heuristics exists. We tested our algorithm on synthetic and real cytogenetic data from renal cell carcinoma. We also compared our learned progression networks with the networks proposed in earlier publications. The software is available on the website https://bitbucket.org/farahani/diprog.

Managing Network Partitions in Structured P2P Networks

Science.gov (United States)

Shafaat, Tallat M.; Ghodsi, Ali; Haridi, Seif

Structured overlay networks form a major class of peer-to-peer systems, which are touted for their abilities to scale, tolerate failures, and self-manage. Any long-lived Internet-scale distributed system is destined to face network partitions. Consequently, the problem of network partitions and mergers is highly related to fault-tolerance and self-management in large-scale systems. This makes it a crucial requirement for building any structured peer-to-peer systems to be resilient to network partitions. Although the problem of network partitions and mergers is highly related to fault-tolerance and self-management in large-scale systems, it has hardly been studied in the context of structured peer-to-peer systems. Structured overlays have mainly been studied under churn (frequent joins/failures), which as a side effect solves the problem of network partitions, as it is similar to massive node failures. Yet, the crucial aspect of network mergers has been ignored. In fact, it has been claimed that ring-based structured overlay networks, which constitute the majority of the structured overlays, are intrinsically ill-suited for merging rings. In this chapter, we motivate the problem of network partitions and mergers in structured overlays. We discuss how a structured overlay can automatically detect a network partition and merger. We present an algorithm for merging multiple similar ring-based overlays when the underlying network merges. We examine the solution in dynamic conditions, showing how our solution is resilient to churn during the merger, something widely believed to be difficult or impossible. We evaluate the algorithm for various scenarios and show that even when falsely detecting a merger, the algorithm quickly terminates and does not clutter the network with many messages. The algorithm is flexible as the tradeoff between message complexity and time complexity can be adjusted by a parameter.

Implicit Structured Sequence Learning: An FMRI Study of the Structural Mere-Exposure Effect

Directory of Open Access Journals (Sweden)

Vasiliki eFolia

2014-02-01

Full Text Available In this event-related FMRI study we investigated the effect of five days of implicit acquisition on preference classification by means of an artificial grammar learning (AGL paradigm based on the structural mere-exposure effect and preference classification using a simple right-linear unification grammar. This allowed us to investigate implicit AGL in a proper learning design by including baseline measurements prior to grammar exposure. After 5 days of implicit acquisition, the FMRI results showed activations in a network of brain regions including the inferior frontal (centered on BA 44/45 and the medial prefrontal regions (centered on BA 8/32. Importantly, and central to this study, the inclusion of a naive preference FMRI baseline measurement allowed us to conclude that these FMRI findings were the intrinsic outcomes of the learning process itself and not a reflection of a preexisting functionality recruited during classification, independent of acquisition. Support for the implicit nature of the knowledge utilized during preference classification on day 5 come from the fact that the basal ganglia, associated with implicit procedural learning, were activated during classification, while the medial temporal lobe system, associated with explicit declarative memory, was consistently deactivated. Thus, preference classification in combination with structural mere-exposure can be used to investigate structural sequence processing (syntax in unsupervised AGL paradigms with proper learning designs.

The Mobile Learning Network: Getting Serious about Games Technologies for Learning

Science.gov (United States)

Petley, Rebecca; Parker, Guy; Attewell, Jill

2011-01-01

The Mobile Learning Network currently in its third year, is a unique collaborative initiative encouraging and enabling the introduction of mobile learning in English post-14 education. The programme, funded jointly by the Learning and Skills Council and participating colleges and schools and supported by LSN has involved nearly 40,000 learners and…

Direct Adaptive Aircraft Control Using Dynamic Cell Structure Neural Networks

Science.gov (United States)

Jorgensen, Charles C.

1997-01-01

A Dynamic Cell Structure (DCS) Neural Network was developed which learns topology representing networks (TRNS) of F-15 aircraft aerodynamic stability and control derivatives. The network is integrated into a direct adaptive tracking controller. The combination produces a robust adaptive architecture capable of handling multiple accident and off- nominal flight scenarios. This paper describes the DCS network and modifications to the parameter estimation procedure. The work represents one step towards an integrated real-time reconfiguration control architecture for rapid prototyping of new aircraft designs. Performance was evaluated using three off-line benchmarks and on-line nonlinear Virtual Reality simulation. Flight control was evaluated under scenarios including differential stabilator lock, soft sensor failure, control and stability derivative variations, and air turbulence.

Learning drifting concepts with neural networks

NARCIS (Netherlands)

Biehl, Michael; Schwarze, Holm

1993-01-01

The learning of time-dependent concepts with a neural network is studied analytically and numerically. The linearly separable target rule is represented by an N-vector, whose time dependence is modelled by a random or deterministic drift process. A single-layer network is trained online using

Fuzzy comprehensive evaluation model of interuniversity collaborative learning based on network

Science.gov (United States)

Wenhui, Ma; Yu, Wang

2017-06-01

Learning evaluation is an effective method, which plays an important role in the network education evaluation system. But most of the current network learning evaluation methods still use traditional university education evaluation system, which do not take into account of web-based learning characteristics, and they are difficult to fit the rapid development of interuniversity collaborative learning based on network. Fuzzy comprehensive evaluation method is used to evaluate interuniversity collaborative learning based on the combination of fuzzy theory and analytic hierarchy process. Analytic hierarchy process is used to determine the weight of evaluation factors of each layer and to carry out the consistency check. According to the fuzzy comprehensive evaluation method, we establish interuniversity collaborative learning evaluation mathematical model. The proposed scheme provides a new thought for interuniversity collaborative learning evaluation based on network.

Maximum entropy methods for extracting the learned features of deep neural networks.

Science.gov (United States)

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Teachers' Motives for Learning in Networks: Costs, Rewards and Community Interest

Science.gov (United States)

van den Beemt, Antoine; Ketelaar, Evelien; Diepstraten, Isabelle; de Laat, Maarten

2018-01-01

Background: This paper discusses teachers' perspectives on learning networks and their motives for participating in these networks. Although it is widely held that teachers' learning may be developed through learning networks, not all teachers participate in such networks. Purpose: The theme of reciprocity, central to studies in the area of…

Didactic Networks: A Proposal for e-learning Content Generation

Directory of Open Access Journals (Sweden)

F. Javier Del Alamo

2010-12-01

Full Text Available The Didactic Networks proposed in this paper are based on previous publications in the field of the RSR (Rhetorical-Semantic Relations. The RSR is a set of primitive relations used for building a specific kind of semantic networks for artificial intelligence applications on the web: the RSN (Rhetorical-Semantic Networks. We bring into focus the RSR application in the field of elearning, by defining Didactic Networks as a new set of semantic patterns oriented to the development of elearning applications. The different lines we offer in our research fall mainly into three levels: (1 The most basic one is in the field of computational linguistics and related to Logical Operations on RSR (RSR Inverses and plurals, RSR combinations, etc, once they have been created. The application of Walter Bosma's results regarding rhetorical distance application and treatment as semantic weighted networks is one of the important issues here. (2 In parallel, we have been working on the creation of a knowledge representation and storage model and data architecture capable of supporting the definition of knowledge networks based on RSR. (3 The third strategic line is in the meso-level, the formulation of a molecular structure of knowledge based on the most frequently used patterns. The main contribution at this level is the set of Fundamental Cognitive Networks (FCN as an application of Novak's mental maps proposal. This paper is part of this third intermediate level, and the Fundamental Didactic Networks (FDN are the result of the application of rhetorical theory procedures to the instructional theory. We have formulated a general set of RSR capable of building discourse, making it possible to express any concept, procedure or principle in terms of knowledge nodes and RSRs. The Instructional knowledge can then be elaborated in the same way. This network structure expressing the instructional knowledge in terms of RSR makes the objective of developing web-learning

On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks.

Directory of Open Access Journals (Sweden)

Paul Tonelli

Full Text Available A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1 the developmental process that links genes to nervous systems, which enables the evolution of large, regular neural networks, and (2 synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT. Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1 in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2 whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities.

Fuzzy comprehensive evaluation model of interuniversity collaborative learning based on network

Directory of Open Access Journals (Sweden)

Wenhui Ma

2017-06-01

Full Text Available Learning evaluation is an effective method, which plays an important role in the network education evaluation system. But most of the current network learning evaluation methods still use traditional university education evaluation system, which do not take into account of web-based learning characteristics, and they are difficult to fit the rapid development of interuniversity collaborative learning based on network. Fuzzy comprehensive evaluation method is used to evaluate interuniversity collaborative learning based on the combination of fuzzy theory and analytic hierarchy process. Analytic hierarchy process is used to determine the weight of evaluation factors of each layer and to carry out the consistency check. According to the fuzzy comprehensive evaluation method, we establish interuniversity collaborative learning evaluation mathematical model. The proposed scheme provides a new thought for interuniversity collaborative learning evaluation based on network.

Community detection in complex networks using deep auto-encoded extreme learning machine

Science.gov (United States)

Wang, Feifan; Zhang, Baihai; Chai, Senchun; Xia, Yuanqing

2018-06-01

Community detection has long been a fascinating topic in complex networks since the community structure usually unveils valuable information of interest. The prevalence and evolution of deep learning and neural networks have been pushing forward the advancement in various research fields and also provide us numerous useful and off the shelf techniques. In this paper, we put the cascaded stacked autoencoders and the unsupervised extreme learning machine (ELM) together in a two-level embedding process and propose a novel community detection algorithm. Extensive comparison experiments in circumstances of both synthetic and real-world networks manifest the advantages of the proposed algorithm. On one hand, it outperforms the k-means clustering in terms of the accuracy and stability thus benefiting from the determinate dimensions of the ELM block and the integration of sparsity restrictions. On the other hand, it endures smaller complexity than the spectral clustering method on account of the shrinkage in time spent on the eigenvalue decomposition procedure.

Social networks as ICT collaborative and supportive learning media ...

African Journals Online (AJOL)

... ICT collaborative and supportive learning media utilisation within the Nigerian educational system. The concept of ICT was concisely explained vis-à-vis the social network concept, theory and collaborative and supportive learning media utilisation. Different types of social network are highlighted among which Facebook, ...

Hybrid E-Learning Tool TransLearning: Video Storytelling to Foster Vicarious Learning within Multi-Stakeholder Collaboration Networks

Science.gov (United States)

van der Meij, Marjoleine G.; Kupper, Frank; Beers, Pieter J.; Broerse, Jacqueline E. W.

2016-01-01

E-learning and storytelling approaches can support informal vicarious learning within geographically widely distributed multi-stakeholder collaboration networks. This case study evaluates hybrid e-learning and video-storytelling approach "TransLearning" by investigation into how its storytelling e-tool supported informal vicarious…

Exploring Practice-Research Networks for Critical Professional Learning

Science.gov (United States)

Appleby, Yvon; Hillier, Yvonne

2012-01-01

This paper discusses the contribution that practice-research networks can make to support critical professional development in the Learning and Skills sector in England. By practice-research networks we mean groups or networks which maintain a connection between research and professional practice. These networks stem from the philosophy of…

Using Social Network and Dropbox in Blended Learning: an Application to University Education

Directory of Open Access Journals (Sweden)

Justo de Jorge Moreno

2012-12-01

Full Text Available The main objective of this study is to analyze the use of the Social Networking and dropbox in blended learning by University students. We try identifying this method, over the student’s performance. The results show that the implementation of blended learning has a positive effect on in learning outcomes. The use of the Knowledge Management process has enabled captures a three-factor structure that reflected the five types of knowledge. The segmentation of the student sample analyzed using cluster technique, has established a clear typology of four groups. Students with higher levels of learning are related to the increased use of resources used and more proactive in blended learning.

From network structure to network reorganization: implications for adult neurogenesis

International Nuclear Information System (INIS)

Schneider-Mizell, Casey M; Zochowski, Michal R; Sander, Leonard M; Parent, Jack M; Ben-Jacob, Eshel

2010-01-01

Networks can be dynamical systems that undergo functional and structural reorganization. One example of such a process is adult hippocampal neurogenesis, in which new cells are continuously born and incorporate into the existing network of the dentate gyrus region of the hippocampus. Many of these introduced cells mature and become indistinguishable from established neurons, joining the existing network. Activity in the network environment is known to promote birth, survival and incorporation of new cells. However, after epileptogenic injury, changes to the connectivity structure around the neurogenic niche are known to correlate with aberrant neurogenesis. The possible role of network-level changes in the development of epilepsy is not well understood. In this paper, we use a computational model to investigate how the structural and functional outcomes of network reorganization, driven by addition of new cells during neurogenesis, depend on the original network structure. We find that there is a stable network topology that allows the network to incorporate new neurons in a manner that enhances activity of the persistently active region, but maintains global network properties. In networks having other connectivity structures, new cells can greatly alter the distribution of firing activity and destroy the initial activity patterns. We thus find that new cells are able to provide focused enhancement of network only for small-world networks with sufficient inhibition. Network-level deviations from this topology, such as those caused by epileptogenic injury, can set the network down a path that develops toward pathological dynamics and aberrant structural integration of new cells

Theoretical framework on selected core issues on conditions for productive learning in networked learning environments

DEFF Research Database (Denmark)

Dirckinck-Holmfeld, Lone; Svendsen, Brian Møller; Ponti, Marisa

The report documents and summarises the elements and dimensions that have been identified to describe and analyse the case studies collected in the Kaleidoscope Jointly Executed Integrating Research Project (JEIRP) on Conditions for productive learning in network learning environments.......The report documents and summarises the elements and dimensions that have been identified to describe and analyse the case studies collected in the Kaleidoscope Jointly Executed Integrating Research Project (JEIRP) on Conditions for productive learning in network learning environments....

Deep Convolutional Neural Networks: Structure, Feature Extraction and Training

Directory of Open Access Journals (Sweden)

Namatēvs Ivars

2017-12-01

Full Text Available Deep convolutional neural networks (CNNs are aimed at processing data that have a known network like topology. They are widely used to recognise objects in images and diagnose patterns in time series data as well as in sensor data classification. The aim of the paper is to present theoretical and practical aspects of deep CNNs in terms of convolution operation, typical layers and basic methods to be used for training and learning. Some practical applications are included for signal and image classification. Finally, the present paper describes the proposed block structure of CNN for classifying crucial features from 3D sensor data.

Logarithmic learning for generalized classifier neural network.

Science.gov (United States)

Ozyildirim, Buse Melis; Avci, Mutlu

2014-12-01

Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network. Copyright © 2014 Elsevier Ltd. All rights reserved.

Towards a Social Networks Model for Online Learning & Performance

Science.gov (United States)

Chung, Kon Shing Kenneth; Paredes, Walter Christian

2015-01-01

In this study, we develop a theoretical model to investigate the association between social network properties, "content richness" (CR) in academic learning discourse, and performance. CR is the extent to which one contributes content that is meaningful, insightful and constructive to aid learning and by social network properties we…

Implicit structured sequence learning: an fMRI study of the structural mere-exposure effect.

Science.gov (United States)

Folia, Vasiliki; Petersson, Karl Magnus

2014-01-01

In this event-related fMRI study we investigated the effect of 5 days of implicit acquisition on preference classification by means of an artificial grammar learning (AGL) paradigm based on the structural mere-exposure effect and preference classification using a simple right-linear unification grammar. This allowed us to investigate implicit AGL in a proper learning design by including baseline measurements prior to grammar exposure. After 5 days of implicit acquisition, the fMRI results showed activations in a network of brain regions including the inferior frontal (centered on BA 44/45) and the medial prefrontal regions (centered on BA 8/32). Importantly, and central to this study, the inclusion of a naive preference fMRI baseline measurement allowed us to conclude that these fMRI findings were the intrinsic outcomes of the learning process itself and not a reflection of a preexisting functionality recruited during classification, independent of acquisition. Support for the implicit nature of the knowledge utilized during preference classification on day 5 come from the fact that the basal ganglia, associated with implicit procedural learning, were activated during classification, while the medial temporal lobe system, associated with explicit declarative memory, was consistently deactivated. Thus, preference classification in combination with structural mere-exposure can be used to investigate structural sequence processing (syntax) in unsupervised AGL paradigms with proper learning designs.

Visualising the invisible: a network approach to reveal the informal social side of student learning.

Science.gov (United States)

Hommes, J; Rienties, B; de Grave, W; Bos, G; Schuwirth, L; Scherpbier, A

2012-12-01

World-wide, universities in health sciences have transformed their curriculum to include collaborative learning and facilitate the students' learning process. Interaction has been acknowledged to be the synergistic element in this learning context. However, students spend the majority of their time outside their classroom and interaction does not stop outside the classroom. Therefore we studied how informal social interaction influences student learning. Moreover, to explore what really matters in the students learning process, a model was tested how the generally known important constructs-prior performance, motivation and social integration-relate to informal social interaction and student learning. 301 undergraduate medical students participated in this cross-sectional quantitative study. Informal social interaction was assessed using self-reported surveys following the network approach. Students' individual motivation, social integration and prior performance were assessed by the Academic Motivation Scale, the College Adaption Questionnaire and students' GPA respectively. A factual knowledge test represented student' learning. All social networks were positively associated with student learning significantly: friendships (β = 0.11), providing information to other students (β = 0.16), receiving information from other students (β = 0.25). Structural equation modelling revealed a model in which social networks increased student learning (r = 0.43), followed by prior performance (r = 0.31). In contrast to prior literature, students' academic motivation and social integration were not associated with students' learning. Students' informal social interaction is strongly associated with students' learning. These findings underline the need to change our focus from the formal context (classroom) to the informal context to optimize student learning and deliver modern medics.

Secondary Structure Prediction of Protein using Resilient Back Propagation Learning Algorithm

Directory of Open Access Journals (Sweden)

Jyotshna Dongardive

2015-12-01

Full Text Available The paper proposes a neural network based approach to predict secondary structure of protein. It uses Multilayer Feed Forward Network (MLFN with resilient back propagation as the learning algorithm. Point Accepted Mutation (PAM is adopted as the encoding scheme and CB396 data set is used for the training and testing of the network. Overall accuracy of the network has been experimentally calculated with different window sizes for the sliding window scheme and by varying the number of units in the hidden layer. The best results were obtained with eleven as the window size and seven as the number of units in the hidden layer.

Network anomaly detection a machine learning perspective

CERN Document Server

Bhattacharyya, Dhruba Kumar

2013-01-01

With the rapid rise in the ubiquity and sophistication of Internet technology and the accompanying growth in the number of network attacks, network intrusion detection has become increasingly important. Anomaly-based network intrusion detection refers to finding exceptional or nonconforming patterns in network traffic data compared to normal behavior. Finding these anomalies has extensive applications in areas such as cyber security, credit card and insurance fraud detection, and military surveillance for enemy activities. Network Anomaly Detection: A Machine Learning Perspective presents mach

SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks.

Science.gov (United States)

Zenke, Friedemann; Ganguli, Surya

2018-04-13

A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns.

Social Networking Sites and Language Learning

Science.gov (United States)

Brick, Billy

2011-01-01

This article examines a study of seven learners who logged their experiences on the language leaning social networking site Livemocha over a period of three months. The features of the site are described and the likelihood of their future success is considered. The learners were introduced to the Social Networking Site (SNS) and asked to learn a…

Structural reliability calculation method based on the dual neural network and direct integration method.

Science.gov (United States)

Li, Haibin; He, Yun; Nie, Xiaobo

2018-01-01

Structural reliability analysis under uncertainty is paid wide attention by engineers and scholars due to reflecting the structural characteristics and the bearing actual situation. The direct integration method, started from the definition of reliability theory, is easy to be understood, but there are still mathematics difficulties in the calculation of multiple integrals. Therefore, a dual neural network method is proposed for calculating multiple integrals in this paper. Dual neural network consists of two neural networks. The neural network A is used to learn the integrand function, and the neural network B is used to simulate the original function. According to the derivative relationships between the network output and the network input, the neural network B is derived from the neural network A. On this basis, the performance function of normalization is employed in the proposed method to overcome the difficulty of multiple integrations and to improve the accuracy for reliability calculations. The comparisons between the proposed method and Monte Carlo simulation method, Hasofer-Lind method, the mean value first-order second moment method have demonstrated that the proposed method is an efficient and accurate reliability method for structural reliability problems.

An examination of a reciprocal relationship between network governance and network structure

DEFF Research Database (Denmark)

Bergenholtz, Carsten; Goduscheit, René Chester

The present article examines the network structure and governance of inter-organisational innovation networks. Network governance refers to the issue of how to manage and coordinate the relational activities and processes in the network while research on network structure deals with the overall...... structural relations between the actors in the network. These streams of research do contain references to each other but mostly rely on a static conception of the relationship between network structure and the applied network governance. The paper is based on a primarily qualitative case study of a loosely...... coupled Danish inter-organisational innovation network. The proposition is that a reciprocal relation between network governance and network structure can be identified....

Learning and forgetting on asymmetric, diluted neural networks

International Nuclear Information System (INIS)

Derrida, B.; Nadal, J.P.

1987-01-01

It is possible to construct diluted asymmetric models of neural networks for which the dynamics can be calculated exactly. The authors test several learning schemes, in particular, models for which the values of the synapses remain bounded and depend on the history. Our analytical results on the relative efficiencies of the various learning schemes are qualitatively similar to the corresponding ones obtained numerically on fully connected symmetric networks

Learning Networks: connecting people, organizations, autonomous agents and learning resources to establish the emergence of effective lifelong learning

NARCIS (Netherlands)

Koper, Rob; Sloep, Peter

2003-01-01

Koper, E.J.R., Sloep, P.B. (2002) Learning Networks connecting people, organizations, autonomous agents and learning resources to establish the emergence of effective lifelong learning. RTD Programma into Learning Technologies 2003-2008. More is different… Heerlen, Nederland: Open Universiteit

Disseminating Innovations in Teaching Value-Based Care Through an Online Learning Network.

Science.gov (United States)

Gupta, Reshma; Shah, Neel T; Moriates, Christopher; Wallingford, September; Arora, Vineet M

2017-08-01

A national imperative to provide value-based care requires new strategies to teach clinicians about high-value care. We developed a virtual online learning network aimed at disseminating emerging strategies in teaching value-based care. The online Teaching Value in Health Care Learning Network includes monthly webinars that feature selected innovators, online discussion forums, and a repository for sharing tools. The learning network comprises clinician-educators and health system leaders across North America. We conducted a cross-sectional online survey of all webinar presenters and the active members of the network, and we assessed program feasibility. Six months after the program launched, there were 277 learning community members in 22 US states. Of the 74 active members, 50 (68%) completed the evaluation. Active members represented independently practicing physicians and trainees in 7 specialties, nurses, educators, and health system leaders. Nearly all speakers reported that the learning network provided them with a unique opportunity to connect with a different audience and achieve greater recognition for their work. Of the members who were active in the learning network, most reported that strategies gleaned from the network were helpful, and some adopted or adapted these innovations at their home institutions. One year after the program launched, the learning network had grown to 364 total members. The learning network helped participants share and implement innovations to promote high-value care. The model can help disseminate innovations in emerging areas of health care transformation, and is sustainable without ongoing support after a period of start-up funding.

A Contextualised Multi-Platform Framework to Support Blended Learning Scenarios in Learning Networks

NARCIS (Netherlands)

De Jong, Tim; Fuertes, Alba; Schmeits, Tally; Specht, Marcus; Koper, Rob

2008-01-01

De Jong, T., Fuertes, A., Schmeits, T., Specht, M., & Koper, R. (2009). A Contextualised Multi-Platform Framework to Support Blended Learning Scenarios in Learning Networks. In D. Goh (Ed.), Multiplatform E-Learning Systems and Technologies: Mobile Devices for Ubiquitous ICT-Based Education (pp.

The neighborhood MCMC sampler for learning Bayesian networks

Science.gov (United States)

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.

Stochastic sensitivity analysis and Langevin simulation for neural network learning

International Nuclear Information System (INIS)

Koda, Masato

1997-01-01

A comprehensive theoretical framework is proposed for the learning of a class of gradient-type neural networks with an additive Gaussian white noise process. The study is based on stochastic sensitivity analysis techniques, and formal expressions are obtained for stochastic learning laws in terms of functional derivative sensitivity coefficients. The present method, based on Langevin simulation techniques, uses only the internal states of the network and ubiquitous noise to compute the learning information inherent in the stochastic correlation between noise signals and the performance functional. In particular, the method does not require the solution of adjoint equations of the back-propagation type. Thus, the present algorithm has the potential for efficiently learning network weights with significantly fewer computations. Application to an unfolded multi-layered network is described, and the results are compared with those obtained by using a back-propagation method

Reinforcement learning account of network reciprocity.

Science.gov (United States)

Ezaki, Takahiro; Masuda, Naoki

2017-01-01

Evolutionary game theory predicts that cooperation in social dilemma games is promoted when agents are connected as a network. However, when networks are fixed over time, humans do not necessarily show enhanced mutual cooperation. Here we show that reinforcement learning (specifically, the so-called Bush-Mosteller model) approximately explains the experimentally observed network reciprocity and the lack thereof in a parameter region spanned by the benefit-to-cost ratio and the node's degree. Thus, we significantly extend previously obtained numerical results.

Boltzmann learning of parameters in cellular neural networks

DEFF Research Database (Denmark)

Hansen, Lars Kai

1992-01-01

The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified...

Multiple brain networks underpinning word learning from fluent speech revealed by independent component analysis.

Science.gov (United States)

López-Barroso, Diana; Ripollés, Pablo; Marco-Pallarés, Josep; Mohammadi, Bahram; Münte, Thomas F; Bachoud-Lévi, Anne-Catherine; Rodriguez-Fornells, Antoni; de Diego-Balaguer, Ruth

2015-04-15

Although neuroimaging studies using standard subtraction-based analysis from functional magnetic resonance imaging (fMRI) have suggested that frontal and temporal regions are involved in word learning from fluent speech, the possible contribution of different brain networks during this type of learning is still largely unknown. Indeed, univariate fMRI analyses cannot identify the full extent of distributed networks that are engaged by a complex task such as word learning. Here we used Independent Component Analysis (ICA) to characterize the different brain networks subserving word learning from an artificial language speech stream. Results were replicated in a second cohort of participants with a different linguistic background. Four spatially independent networks were associated with the task in both cohorts: (i) a dorsal Auditory-Premotor network; (ii) a dorsal Sensory-Motor network; (iii) a dorsal Fronto-Parietal network; and (iv) a ventral Fronto-Temporal network. The level of engagement of these networks varied through the learning period with only the dorsal Auditory-Premotor network being engaged across all blocks. In addition, the connectivity strength of this network in the second block of the learning phase correlated with the individual variability in word learning performance. These findings suggest that: (i) word learning relies on segregated connectivity patterns involving dorsal and ventral networks; and (ii) specifically, the dorsal auditory-premotor network connectivity strength is directly correlated with word learning performance. Copyright © 2015 Elsevier Inc. All rights reserved.

The Student Experience of Learning Using Networked Technologies: An Emergent Progression of Expanding Awareness

Science.gov (United States)

Cutajar, Maria

2017-01-01

This article reports on phenomenographic research which explored the qualitative differences in post-secondary students' accounts of their networked learning experiences. Data was generated using semi-structured interviews with a purposive sample of participants. Phenomenographic analysis led to a configuration of variation in students' accounts…

Network structure exploration via Bayesian nonparametric models

International Nuclear Information System (INIS)

Chen, Y; Wang, X L; Xiang, X; Tang, B Z; Bu, J Z

2015-01-01

Complex networks provide a powerful mathematical representation of complex systems in nature and society. To understand complex networks, it is crucial to explore their internal structures, also called structural regularities. The task of network structure exploration is to determine how many groups there are in a complex network and how to group the nodes of the network. Most existing structure exploration methods need to specify either a group number or a certain type of structure when they are applied to a network. In the real world, however, the group number and also the certain type of structure that a network has are usually unknown in advance. To explore structural regularities in complex networks automatically, without any prior knowledge of the group number or the certain type of structure, we extend a probabilistic mixture model that can handle networks with any type of structure but needs to specify a group number using Bayesian nonparametric theory. We also propose a novel Bayesian nonparametric model, called the Bayesian nonparametric mixture (BNPM) model. Experiments conducted on a large number of networks with different structures show that the BNPM model is able to explore structural regularities in networks automatically with a stable, state-of-the-art performance. (paper)

Collaborative Supervised Learning for Sensor Networks

Science.gov (United States)

Wagstaff, Kiri L.; Rebbapragada, Umaa; Lane, Terran

2011-01-01

Collaboration methods for distributed machine-learning algorithms involve the specification of communication protocols for the learners, which can query other learners and/or broadcast their findings preemptively. Each learner incorporates information from its neighbors into its own training set, and they are thereby able to bootstrap each other to higher performance. Each learner resides at a different node in the sensor network and makes observations (collects data) independently of the other learners. After being seeded with an initial labeled training set, each learner proceeds to learn in an iterative fashion. New data is collected and classified. The learner can then either broadcast its most confident classifications for use by other learners, or can query neighbors for their classifications of its least confident items. As such, collaborative learning combines elements of both passive (broadcast) and active (query) learning. It also uses ideas from ensemble learning to combine the multiple responses to a given query into a single useful label. This approach has been evaluated against current non-collaborative alternatives, including training a single classifier and deploying it at all nodes with no further learning possible, and permitting learners to learn from their own most confident judgments, absent interaction with their neighbors. On several data sets, it has been consistently found that active collaboration is the best strategy for a distributed learner network. The main advantages include the ability for learning to take place autonomously by collaboration rather than by requiring intervention from an oracle (usually human), and also the ability to learn in a distributed environment, permitting decisions to be made in situ and to yield faster response time.

Learning Errors by Radial Basis Function Neural Networks and Regularization Networks

Czech Academy of Sciences Publication Activity Database

Neruda, Roman; Vidnerová, Petra

2009-01-01

Roč. 1, č. 2 (2009), s. 49-57 ISSN 2005-4262 R&D Projects: GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : neural network * RBF networks * regularization * learning Subject RIV: IN - Informatics, Computer Science http://www.sersc.org/journals/IJGDC/vol2_no1/5.pdf

Learning State Space Dynamics in Recurrent Networks

Science.gov (United States)

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.

Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization.

Science.gov (United States)

Kulkarni, Shruti R; Rajendran, Bipin

2018-07-01

We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. Copyright © 2018 Elsevier Ltd. All rights reserved.

Networks: structure and action : steering in and steering by policy networks

NARCIS (Netherlands)

Dassen, A.

2010-01-01

This thesis explores the opportunities to build a structural policy network model that is rooted in social network theories. By making a distinction between a process of steering in networks, and a process of steering by networks, it addresses the effects of network structures on network dynamics as

Problems in the Deployment of Learning Networks In Small Organizations

NARCIS (Netherlands)

Shankle, Dean E.; Shankle, Jeremy P.

2006-01-01

Please, cite this publication as: Shankle, D.E., & Shankle, J.P. (2006). Problems in the Deployment of Learning Networks In Small Organizations. Proceedings of International Workshop in Learning Networks for Lifelong Competence Development, TENCompetence Conference. March 30th-31st, Sofia, Bulgaria:

Parameter diagnostics of phases and phase transition learning by neural networks

Science.gov (United States)

Suchsland, Philippe; Wessel, Stefan

2018-05-01

We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

Reinforcement learning account of network reciprocity.

Directory of Open Access Journals (Sweden)

Takahiro Ezaki

Full Text Available Evolutionary game theory predicts that cooperation in social dilemma games is promoted when agents are connected as a network. However, when networks are fixed over time, humans do not necessarily show enhanced mutual cooperation. Here we show that reinforcement learning (specifically, the so-called Bush-Mosteller model approximately explains the experimentally observed network reciprocity and the lack thereof in a parameter region spanned by the benefit-to-cost ratio and the node's degree. Thus, we significantly extend previously obtained numerical results.

A linear programming approach for estimating the structure of a sparse linear genetic network from transcript profiling data

Directory of Open Access Journals (Sweden)

Chandra Nagasuma R

2009-02-01

Full Text Available Abstract Background A genetic network can be represented as a directed graph in which a node corresponds to a gene and a directed edge specifies the direction of influence of one gene on another. The reconstruction of such networks from transcript profiling data remains an important yet challenging endeavor. A transcript profile specifies the abundances of many genes in a biological sample of interest. Prevailing strategies for learning the structure of a genetic network from high-dimensional transcript profiling data assume sparsity and linearity. Many methods consider relatively small directed graphs, inferring graphs with up to a few hundred nodes. This work examines large undirected graphs representations of genetic networks, graphs with many thousands of nodes where an undirected edge between two nodes does not indicate the direction of influence, and the problem of estimating the structure of such a sparse linear genetic network (SLGN from transcript profiling data. Results The structure learning task is cast as a sparse linear regression problem which is then posed as a LASSO (l1-constrained fitting problem and solved finally by formulating a Linear Program (LP. A bound on the Generalization Error of this approach is given in terms of the Leave-One-Out Error. The accuracy and utility of LP-SLGNs is assessed quantitatively and qualitatively using simulated and real data. The Dialogue for Reverse Engineering Assessments and Methods (DREAM initiative provides gold standard data sets and evaluation metrics that enable and facilitate the comparison of algorithms for deducing the structure of networks. The structures of LP-SLGNs estimated from the INSILICO1, INSILICO2 and INSILICO3 simulated DREAM2 data sets are comparable to those proposed by the first and/or second ranked teams in the DREAM2 competition. The structures of LP-SLGNs estimated from two published Saccharomyces cerevisae cell cycle transcript profiling data sets capture known

The Relationships Between Policy, Boundaries and Research in Networked Learning

DEFF Research Database (Denmark)

Ryberg, Thomas; Sinclair, Christine

2016-01-01

the books that include a selection of reworked and peer-reviewed papers from the conference. The 2014 Networked Learning Conference which was held in Edinburgh was characterised by animated dialogue on emergent influences affecting networked teaching and learning building on work established in earlier...

The Impacts of Network Centrality and Self-Regulation on an E-Learning Environment with the Support of Social Network Awareness

Science.gov (United States)

Lin, Jian-Wei; Huang, Hsieh-Hong; Chuang, Yuh-Shy

2015-01-01

An e-learning environment that supports social network awareness (SNA) is a highly effective means of increasing peer interaction and assisting student learning by raising awareness of social and learning contexts of peers. Network centrality profoundly impacts student learning in an SNA-related e-learning environment. Additionally,…

Continuous Online Sequence Learning with an Unsupervised Neural Network Model.

Science.gov (United States)

Cui, Yuwei; Ahmad, Subutar; Hawkins, Jeff

2016-09-14

The ability to recognize and predict temporal sequences of sensory inputs is vital for survival in natural environments. Based on many known properties of cortical neurons, hierarchical temporal memory (HTM) sequence memory recently has been proposed as a theoretical framework for sequence learning in the cortex. In this letter, we analyze properties of HTM sequence memory and apply it to sequence learning and prediction problems with streaming data. We show the model is able to continuously learn a large number of variableorder temporal sequences using an unsupervised Hebbian-like learning rule. The sparse temporal codes formed by the model can robustly handle branching temporal sequences by maintaining multiple predictions until there is sufficient disambiguating evidence. We compare the HTM sequence memory with other sequence learning algorithms, including statistical methods: autoregressive integrated moving average; feedforward neural networks-time delay neural network and online sequential extreme learning machine; and recurrent neural networks-long short-term memory and echo-state networks on sequence prediction problems with both artificial and real-world data. The HTM model achieves comparable accuracy to other state-of-the-art algorithms. The model also exhibits properties that are critical for sequence learning, including continuous online learning, the ability to handle multiple predictions and branching sequences with high-order statistics, robustness to sensor noise and fault tolerance, and good performance without task-specific hyperparameter tuning. Therefore, the HTM sequence memory not only advances our understanding of how the brain may solve the sequence learning problem but is also applicable to real-world sequence learning problems from continuous data streams.

The TENCompetence Infrastructure: A Learning Network Implementation

Science.gov (United States)

Vogten, Hubert; Martens, Harrie; Lemmers, Ruud

The TENCompetence project developed a first release of a Learning Network infrastructure to support individuals, groups and organisations in professional competence development. This infrastructure Learning Network infrastructure was released as open source to the community thereby allowing users and organisations to use and contribute to this development as they see fit. The infrastructure consists of client applications providing the user experience and server components that provide the services to these clients. These services implement the domain model (Koper 2006) by provisioning the entities of the domain model (see also Sect. 18.4) and henceforth will be referenced as domain entity services.

Modeling a Neural Network as a Teaching Tool for the Learning of the Structure-Function Relationship

Science.gov (United States)

Salinas, Dino G.; Acevedo, Cristian; Gomez, Christian R.

2010-01-01

The authors describe an activity they have created in which students can visualize a theoretical neural network whose states evolve according to a well-known simple law. This activity provided an uncomplicated approach to a paradigm commonly represented through complex mathematical formulation. From their observations, students learned many basic…

A theoretical design for learning model addressing the networked society

DEFF Research Database (Denmark)

Levinsen, Karin; Nielsen, Janni; Sørensen, Birgitte Holm

2010-01-01

The transition from the industrial to the networked society produces contradictions that challenges the educational system and force it to adapt to new conditions. In a Danish virtual Master in Information and Communication Technologies and Learning (MIL) these contradictions appear as a field of...... which enables students to develop Networked Society competencies and maintain progression in the learning process also during the online periods. Additionally we suggest that our model contributes to the innovation of a networked society's design for learning....... is continuously decreasing. We teach for deep learning but are confronted by students' cost-benefit strategies when they navigate through the study programme under time pressure. To meet these challenges a Design for Learning Model has been developed. The aim is to provide a scaffold that ensures students......' acquisition of the subject matter within a time limit and at a learning quality that support their deep learning process during a subsequent period of on-line study work. In the process of moving from theory to application the model passes through three stages: 1) Conceptual modelling; 2) Orchestration, and 3...

Detecting Hierarchical Structure in Networks

DEFF Research Database (Denmark)

Herlau, Tue; Mørup, Morten; Schmidt, Mikkel Nørgaard

2012-01-01

Many real-world networks exhibit hierarchical organization. Previous models of hierarchies within relational data has focused on binary trees; however, for many networks it is unknown whether there is hierarchical structure, and if there is, a binary tree might not account well for it. We propose...... a generative Bayesian model that is able to infer whether hierarchies are present or not from a hypothesis space encompassing all types of hierarchical tree structures. For efficient inference we propose a collapsed Gibbs sampling procedure that jointly infers a partition and its hierarchical structure....... On synthetic and real data we demonstrate that our model can detect hierarchical structure leading to better link-prediction than competing models. Our model can be used to detect if a network exhibits hierarchical structure, thereby leading to a better comprehension and statistical account the network....

European networks in structural integrity

International Nuclear Information System (INIS)

Crutzen, S.; Davies, M.; Hemsworth, B.; Hurst, R.; Kussmaul, K.

1994-01-01

Several institutions and electrical utilities in Europe, including the Joint Research Centre (JRC) have the capability to deal problems posed by the operation and ageing of structural components and with their structural integrity assessment. These institutions and the JRC have developed cooperative programmes now organised in networks. They include utilities, engineering companies, R and D laboratories and Regulatory Bodies. Networks are organised and managed like the successful PISC programme: The Institute for Advanced Materials of JRC plays the role of Operating Agent and Manager of these networks: ENIQ, AMES, NESC, each of them dealing with a specific aspect of fitness for purpose of materials in structural components. There exist strong links between the networks and EC Working Groups on Structural Integrity Codes and Standards. (orig.)

Collective network for computer structures

Science.gov (United States)

Blumrich, Matthias A [Ridgefield, CT; Coteus, Paul W [Yorktown Heights, NY; Chen, Dong [Croton On Hudson, NY; Gara, Alan [Mount Kisco, NY; Giampapa, Mark E [Irvington, NY; Heidelberger, Philip [Cortlandt Manor, NY; Hoenicke, Dirk [Ossining, NY; Takken, Todd E [Brewster, NY; Steinmacher-Burow, Burkhard D [Wernau, DE; Vranas, Pavlos M [Bedford Hills, NY

2011-08-16

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices ate included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network and class structures. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to needs of a processing algorithm.

Relationship between neuronal network architecture and naming performance in temporal lobe epilepsy: A connectome based approach using machine learning.

Science.gov (United States)

Munsell, B C; Wu, G; Fridriksson, J; Thayer, K; Mofrad, N; Desisto, N; Shen, D; Bonilha, L

2017-09-09

Impaired confrontation naming is a common symptom of temporal lobe epilepsy (TLE). The neurobiological mechanisms underlying this impairment are poorly understood but may indicate a structural disorganization of broadly distributed neuronal networks that support naming ability. Importantly, naming is frequently impaired in other neurological disorders and by contrasting the neuronal structures supporting naming in TLE with other diseases, it will become possible to elucidate the common systems supporting naming. We aimed to evaluate the neuronal networks that support naming in TLE by using a machine learning algorithm intended to predict naming performance in subjects with medication refractory TLE using only the structural brain connectome reconstructed from diffusion tensor imaging. A connectome-based prediction framework was developed using network properties from anatomically defined brain regions across the entire brain, which were used in a multi-task machine learning algorithm followed by support vector regression. Nodal eigenvector centrality, a measure of regional network integration, predicted approximately 60% of the variance in naming. The nodes with the highest regression weight were bilaterally distributed among perilimbic sub-networks involving mainly the medial and lateral temporal lobe regions. In the context of emerging evidence regarding the role of large structural networks that support language processing, our results suggest intact naming relies on the integration of sub-networks, as opposed to being dependent on isolated brain areas. In the case of TLE, these sub-networks may be disproportionately indicative naming processes that are dependent semantic integration from memory and lexical retrieval, as opposed to multi-modal perception or motor speech production. Copyright © 2017. Published by Elsevier Inc.

Relationships between music training, speech processing, and word learning: a network perspective.

Science.gov (United States)

Elmer, Stefan; Jäncke, Lutz

2018-03-15

Numerous studies have documented the behavioral advantages conferred on professional musicians and children undergoing music training in processing speech sounds varying in the spectral and temporal dimensions. These beneficial effects have previously often been associated with local functional and structural changes in the auditory cortex (AC). However, this perspective is oversimplified, in that it does not take into account the intrinsic organization of the human brain, namely, neural networks and oscillatory dynamics. Therefore, we propose a new framework for extending these previous findings to a network perspective by integrating multimodal imaging, electrophysiology, and neural oscillations. In particular, we provide concrete examples of how functional and structural connectivity can be used to model simple neural circuits exerting a modulatory influence on AC activity. In addition, we describe how such a network approach can be used for better comprehending the beneficial effects of music training on more complex speech functions, such as word learning. © 2018 New York Academy of Sciences.

Comparison between extreme learning machine and wavelet neural networks in data classification

Science.gov (United States)

Yahia, Siwar; Said, Salwa; Jemai, Olfa; Zaied, Mourad; Ben Amar, Chokri

2017-03-01

Extreme learning Machine is a well known learning algorithm in the field of machine learning. It's about a feed forward neural network with a single-hidden layer. It is an extremely fast learning algorithm with good generalization performance. In this paper, we aim to compare the Extreme learning Machine with wavelet neural networks, which is a very used algorithm. We have used six benchmark data sets to evaluate each technique. These datasets Including Wisconsin Breast Cancer, Glass Identification, Ionosphere, Pima Indians Diabetes, Wine Recognition and Iris Plant. Experimental results have shown that both extreme learning machine and wavelet neural networks have reached good results.

Validating module network learning algorithms using simulated data.

Science.gov (United States)

Michoel, Tom; Maere, Steven; Bonnet, Eric; Joshi, Anagha; Saeys, Yvan; Van den Bulcke, Tim; Van Leemput, Koenraad; van Remortel, Piet; Kuiper, Martin; Marchal, Kathleen; Van de Peer, Yves

2007-05-03

In recent years, several authors have used probabilistic graphical models to learn expression modules and their regulatory programs from gene expression data. Despite the demonstrated success of such algorithms in uncovering biologically relevant regulatory relations, further developments in the area are hampered by a lack of tools to compare the performance of alternative module network learning strategies. Here, we demonstrate the use of the synthetic data generator SynTReN for the purpose of testing and comparing module network learning algorithms. We introduce a software package for learning module networks, called LeMoNe, which incorporates a novel strategy for learning regulatory programs. Novelties include the use of a bottom-up Bayesian hierarchical clustering to construct the regulatory programs, and the use of a conditional entropy measure to assign regulators to the regulation program nodes. Using SynTReN data, we test the performance of LeMoNe in a completely controlled situation and assess the effect of the methodological changes we made with respect to an existing software package, namely Genomica. Additionally, we assess the effect of various parameters, such as the size of the data set and the amount of noise, on the inference performance. Overall, application of Genomica and LeMoNe to simulated data sets gave comparable results. However, LeMoNe offers some advantages, one of them being that the learning process is considerably faster for larger data sets. Additionally, we show that the location of the regulators in the LeMoNe regulation programs and their conditional entropy may be used to prioritize regulators for functional validation, and that the combination of the bottom-up clustering strategy with the conditional entropy-based assignment of regulators improves the handling of missing or hidden regulators. We show that data simulators such as SynTReN are very well suited for the purpose of developing, testing and improving module network

Gamification of learning deactivates the Default Mode Network

Directory of Open Access Journals (Sweden)

Paul Alexander Howard-Jones

2016-01-01

Full Text Available We hypothesised that embedding educational learning in a game would improve learning outcomes, with increased engagement and recruitment of cognitive resources evidenced by increased activation of working memory network (WMN and deactivation of Default Mode Network (DMN regions. In an fMRI study, we compared activity during periods of learning in three conditions that were increasingly game-like: Study-only (when periods of learning were followed by an exemplar question together with its correct answer, Self-quizzing (when periods of learning were followed by a multiple choice question in return for a fixed number of points and Game-based (when, following each period of learning, participants competed with a peer to answer the question for escalating, uncertain rewards. DMN hubs deactivated as conditions became more game-like, alongside greater self-reported engagement and, in the Game-based condition, higher learning scores. These changes did not occur with any detectable increase in WMN activity. Additionally, ventral striatal activation was associated with responding to questions and receiving positive question feedback. Results support the significance of DMN deactivation for educational learning, and are aligned with recent evidence suggesting DMN and WMN activity may not always be anti-correlated.

Gamification of Learning Deactivates the Default Mode Network.

Science.gov (United States)

Howard-Jones, Paul A; Jay, Tim; Mason, Alice; Jones, Harvey

2015-01-01

We hypothesized that embedding educational learning in a game would improve learning outcomes, with increased engagement and recruitment of cognitive resources evidenced by increased activation of working memory network (WMN) and deactivation of default mode network (DMN) regions. In an fMRI study, we compared activity during periods of learning in three conditions that were increasingly game-like: Study-only (when periods of learning were followed by an exemplar question together with its correct answer), Self-quizzing (when periods of learning were followed by a multiple choice question in return for a fixed number of points) and Game-based (when, following each period of learning, participants competed with a peer to answer the question for escalating, uncertain rewards). DMN hubs deactivated as conditions became more game-like, alongside greater self-reported engagement and, in the Game-based condition, higher learning scores. These changes did not occur with any detectable increase in WMN activity. Additionally, ventral striatal activation was associated with responding to questions and receiving positive question feedback. Results support the significance of DMN deactivation for educational learning, and are aligned with recent evidence suggesting DMN and WMN activity may not always be anti-correlated.

Bayesian Inference and Online Learning in Poisson Neuronal Networks.

Science.gov (United States)

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.

Aero Engine Component Fault Diagnosis Using Multi-Hidden-Layer Extreme Learning Machine with Optimized Structure

Directory of Open Access Journals (Sweden)

Shan Pang

2016-01-01

Full Text Available A new aero gas turbine engine gas path component fault diagnosis method based on multi-hidden-layer extreme learning machine with optimized structure (OM-ELM was proposed. OM-ELM employs quantum-behaved particle swarm optimization to automatically obtain the optimal network structure according to both the root mean square error on training data set and the norm of output weights. The proposed method is applied to handwritten recognition data set and a gas turbine engine diagnostic application and is compared with basic ELM, multi-hidden-layer ELM, and two state-of-the-art deep learning algorithms: deep belief network and the stacked denoising autoencoder. Results show that, with optimized network structure, OM-ELM obtains better test accuracy in both applications and is more robust to sensor noise. Meanwhile it controls the model complexity and needs far less hidden nodes than multi-hidden-layer ELM, thus saving computer memory and making it more efficient to implement. All these advantages make our method an effective and reliable tool for engine component fault diagnosis tool.

Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks

Directory of Open Access Journals (Sweden)

Hasan A. A. Al-Rawi

2014-01-01

Full Text Available Cognitive radio (CR enables unlicensed users (or secondary users, SUs to sense for and exploit underutilized licensed spectrum owned by the licensed users (or primary users, PUs. Reinforcement learning (RL is an artificial intelligence approach that enables a node to observe, learn, and make appropriate decisions on action selection in order to maximize network performance. Routing enables a source node to search for a least-cost route to its destination node. While there have been increasing efforts to enhance the traditional RL approach for routing in wireless networks, this research area remains largely unexplored in the domain of routing in CR networks. This paper applies RL in routing and investigates the effects of various features of RL (i.e., reward function, exploitation, and exploration, as well as learning rate through simulation. New approaches and recommendations are proposed to enhance the features in order to improve the network performance brought about by RL to routing. Simulation results show that the RL parameters of the reward function, exploitation, and exploration, as well as learning rate, must be well regulated, and the new approaches proposed in this paper improves SUs’ network performance without significantly jeopardizing PUs’ network performance, specifically SUs’ interference to PUs.

A Newton-type neural network learning algorithm

International Nuclear Information System (INIS)

Ivanov, V.V.; Puzynin, I.V.; Purehvdorzh, B.

1993-01-01

First- and second-order learning methods for feed-forward multilayer networks are considered. A Newton-type algorithm is proposed and compared with the common back-propagation algorithm. It is shown that the proposed algorithm provides better learning quality. Some recommendations for their usage are given. 11 refs.; 1 fig.; 1 tab

Markov models for fMRI correlation structure: Is brain functional connectivity small world, or decomposable into networks?

Science.gov (United States)

Varoquaux, G; Gramfort, A; Poline, J B; Thirion, B

2012-01-01

Correlations in the signal observed via functional Magnetic Resonance Imaging (fMRI), are expected to reveal the interactions in the underlying neural populations through hemodynamic response. In particular, they highlight distributed set of mutually correlated regions that correspond to brain networks related to different cognitive functions. Yet graph-theoretical studies of neural connections give a different picture: that of a highly integrated system with small-world properties: local clustering but with short pathways across the complete structure. We examine the conditional independence properties of the fMRI signal, i.e. its Markov structure, to find realistic assumptions on the connectivity structure that are required to explain the observed functional connectivity. In particular we seek a decomposition of the Markov structure into segregated functional networks using decomposable graphs: a set of strongly-connected and partially overlapping cliques. We introduce a new method to efficiently extract such cliques on a large, strongly-connected graph. We compare methods learning different graph structures from functional connectivity by testing the goodness of fit of the model they learn on new data. We find that summarizing the structure as strongly-connected networks can give a good description only for very large and overlapping networks. These results highlight that Markov models are good tools to identify the structure of brain connectivity from fMRI signals, but for this purpose they must reflect the small-world properties of the underlying neural systems. Copyright © 2012 Elsevier Ltd. All rights reserved.

Learning in innovation networks: Some simulation experiments

Science.gov (United States)

Gilbert, Nigel; Ahrweiler, Petra; Pyka, Andreas

2007-05-01

According to the organizational learning literature, the greatest competitive advantage a firm has is its ability to learn. In this paper, a framework for modeling learning competence in firms is presented to improve the understanding of managing innovation. Firms with different knowledge stocks attempt to improve their economic performance by engaging in radical or incremental innovation activities and through partnerships and networking with other firms. In trying to vary and/or to stabilize their knowledge stocks by organizational learning, they attempt to adapt to environmental requirements while the market strongly selects on the results. The simulation experiments show the impact of different learning activities, underlining the importance of innovation and learning.

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

Science.gov (United States)

Williams-Hayes, Peggy S.

2004-01-01

The NASA F-15 Intelligent Flight Control System project team developed a series of flight control concepts designed to demonstrate neural network-based adaptive controller benefits, with the objective to develop and flight-test control systems using neural network technology to optimize aircraft performance under nominal conditions and stabilize the aircraft under failure conditions. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to baseline aerodynamic derivatives in flight. This open-loop flight test set was performed in preparation for a future phase in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed - pitch frequency sweep and automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. Flight data examination shows that addition of flight-identified aerodynamic derivative increments into the simulation improved aircraft pitch handling qualities.

Pinning Control Strategy of Multicommunity Structure Networks

Directory of Open Access Journals (Sweden)

Chao Ding

2017-01-01

Full Text Available In order to investigate the effects of community structure on synchronization, a pinning control strategy is researched in a class of complex networks with community structure in this paper. A feedback control law is designed based on the network community structure information. The stability condition is given and proved by using Lyapunov stability theory. Our research shows that as to community structure networks, there being a threshold hT≈5, when coupling strength bellows this threshold, the stronger coupling strength corresponds to higher synchronizability; vice versa, the stronger coupling strength brings lower synchronizability. In addition the synchronizability of overlapping and nonoverlapping community structure networks was simulated and analyzed; while the nodes were controlled randomly and intensively, the results show that intensive control strategy is better than the random one. The network will reach synchronization easily when the node with largest betweenness was controlled. Furthermore, four difference networks’ synchronizability, such as Barabási-Albert network, Watts-Strogatz network, Erdös-Rényi network, and community structure network, are simulated; the research shows that the community structure network is more easily synchronized under the same control strength.

Networking for Learning The role of Networking in a Lifelong Learner's Professional Development

NARCIS (Netherlands)

Rajagopal, Kamakshi

2016-01-01

This dissertation discusses the role the social activity of networking plays in lifelong learners’ professional and personal continuous development. The main hypothesis of this thesis is that networking is a learning strategy for lifelong learners, in which conversations are key activities through

Using Epistemic Network Analysis to understand core topics as planned learning objectives

DEFF Research Database (Denmark)

Allsopp, Benjamin Brink; Dreyøe, Jonas; Misfeldt, Morten

Epistemic Network Analysis is a tool developed by the epistemic games group at the University of Wisconsin Madison for tracking the relations between concepts in students discourse (Shaffer 2017). In our current work we are applying this tool to learning objectives in teachers digital preparation....... The danish mathematics curriculum is organised in six competencies and three topics. In the recently implemented learning platforms teacher choose which of the mathematical competencies that serves as objective for a specific lesson or teaching sequence. Hence learning objectives for lessons and teaching...... sequences are defining a network of competencies, where two competencies are closely related of they often are part of the same learning objective or teaching sequence. We are currently using Epistemic Network Analysis to study these networks. In the poster we will include examples of different networks...

True Nature of Supply Network Communication Structure

Directory of Open Access Journals (Sweden)

Lokhman Hakim bin Osman

2016-04-01

Full Text Available Globalization of world economy has altered the definition of organizational structure. Global supply chain can no longer be viewed as an arm-length structure. It has become more complex. The complexity demands deeper research and understanding. This research analyzed a structure of supply network in an attempt to elucidate the true structure of the supply network. Using the quantitative Social Network Analysis methodology, findings of this study indicated that, the structure of the supply network differs depending on the types of network relations. An important implication of these findings would be a more focus resource management upon network relationship development that is based on firms’ positions in the different network structure. This research also contributes to the various strategies of effective and efficient supply chain management.

Learning-induced pattern classification in a chaotic neural network

International Nuclear Information System (INIS)

Li, Yang; Zhu, Ping; Xie, Xiaoping; He, Guoguang; Aihara, Kazuyuki

2012-01-01

In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition. -- Highlights: ► Proposing a Hebbian learning rule with passive forgetting (HLRPF). ► Defining indices to investigate the evolution of the weights simply. ► The chaotic neural network with HLRPF acts as a fuzzy-like pattern classifier. ► The pattern classifier ability of the network is improved much.

Attentional Bias in Human Category Learning: The Case of Deep Learning.

Science.gov (United States)

Hanson, Catherine; Caglar, Leyla Roskan; Hanson, Stephen José

2018-01-01

Category learning performance is influenced by both the nature of the category's structure and the way category features are processed during learning. Shepard (1964, 1987) showed that stimuli can have structures with features that are statistically uncorrelated (separable) or statistically correlated (integral) within categories. Humans find it much easier to learn categories having separable features, especially when attention to only a subset of relevant features is required, and harder to learn categories having integral features, which require consideration of all of the available features and integration of all the relevant category features satisfying the category rule (Garner, 1974). In contrast to humans, a single hidden layer backpropagation (BP) neural network has been shown to learn both separable and integral categories equally easily, independent of the category rule (Kruschke, 1993). This "failure" to replicate human category performance appeared to be strong evidence that connectionist networks were incapable of modeling human attentional bias. We tested the presumed limitations of attentional bias in networks in two ways: (1) by having networks learn categories with exemplars that have high feature complexity in contrast to the low dimensional stimuli previously used, and (2) by investigating whether a Deep Learning (DL) network, which has demonstrated humanlike performance in many different kinds of tasks (language translation, autonomous driving, etc.), would display human-like attentional bias during category learning. We were able to show a number of interesting results. First, we replicated the failure of BP to differentially process integral and separable category structures when low dimensional stimuli are used (Garner, 1974; Kruschke, 1993). Second, we show that using the same low dimensional stimuli, Deep Learning (DL), unlike BP but similar to humans, learns separable category structures more quickly than integral category structures

Attentional Bias in Human Category Learning: The Case of Deep Learning

Directory of Open Access Journals (Sweden)

Catherine Hanson

2018-04-01

Full Text Available Category learning performance is influenced by both the nature of the category's structure and the way category features are processed during learning. Shepard (1964, 1987 showed that stimuli can have structures with features that are statistically uncorrelated (separable or statistically correlated (integral within categories. Humans find it much easier to learn categories having separable features, especially when attention to only a subset of relevant features is required, and harder to learn categories having integral features, which require consideration of all of the available features and integration of all the relevant category features satisfying the category rule (Garner, 1974. In contrast to humans, a single hidden layer backpropagation (BP neural network has been shown to learn both separable and integral categories equally easily, independent of the category rule (Kruschke, 1993. This “failure” to replicate human category performance appeared to be strong evidence that connectionist networks were incapable of modeling human attentional bias. We tested the presumed limitations of attentional bias in networks in two ways: (1 by having networks learn categories with exemplars that have high feature complexity in contrast to the low dimensional stimuli previously used, and (2 by investigating whether a Deep Learning (DL network, which has demonstrated humanlike performance in many different kinds of tasks (language translation, autonomous driving, etc., would display human-like attentional bias during category learning. We were able to show a number of interesting results. First, we replicated the failure of BP to differentially process integral and separable category structures when low dimensional stimuli are used (Garner, 1974; Kruschke, 1993. Second, we show that using the same low dimensional stimuli, Deep Learning (DL, unlike BP but similar to humans, learns separable category structures more quickly than integral category

Airline network structure in competitive market

Directory of Open Access Journals (Sweden)

Babić Danica D.

2014-01-01

Full Text Available Airline's network is the key element of its business strategy and selected network structure will not have influence only on the airline's costs but could gain some advantage in revenues, too. Network designing implies that an airline has to make decisions about markets that it will serve and how to serve those markets. Network choice raises the following questions for an airline: a what markets to serve, b how to serve selected markets, c what level of service to offer, d what are the benefits/cost of the that decisions and e what is the influence of the competition. We analyzed the existing airline business models and corresponding network structure. The paper highlights the relationship between the network structures and the airline business strategies. Using a simple model we examine the relationship between the network structure and service quality in deregulated market.

Nonlinear dynamic systems identification using recurrent interval type-2 TSK fuzzy neural network - A novel structure.

Science.gov (United States)

El-Nagar, Ahmad M

2018-01-01

In this study, a novel structure of a recurrent interval type-2 Takagi-Sugeno-Kang (TSK) fuzzy neural network (FNN) is introduced for nonlinear dynamic and time-varying systems identification. It combines the type-2 fuzzy sets (T2FSs) and a recurrent FNN to avoid the data uncertainties. The fuzzy firing strengths in the proposed structure are returned to the network input as internal variables. The interval type-2 fuzzy sets (IT2FSs) is used to describe the antecedent part for each rule while the consequent part is a TSK-type, which is a linear function of the internal variables and the external inputs with interval weights. All the type-2 fuzzy rules for the proposed RIT2TSKFNN are learned on-line based on structure and parameter learning, which are performed using the type-2 fuzzy clustering. The antecedent and consequent parameters of the proposed RIT2TSKFNN are updated based on the Lyapunov function to achieve network stability. The obtained results indicate that our proposed network has a small root mean square error (RMSE) and a small integral of square error (ISE) with a small number of rules and a small computation time compared with other type-2 FNNs. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Towards structural controllability of local-world networks

International Nuclear Information System (INIS)

Sun, Shiwen; Ma, Yilin; Wu, Yafang; Wang, Li; Xia, Chengyi

2016-01-01

Controlling complex networks is of vital importance in science and engineering. Meanwhile, local-world effect is an important ingredient which should be taken into consideration in the complete description of real-world complex systems. In this letter, structural controllability of a class of local-world networks is investigated. Through extensive numerical simulations, firstly, effects of local world size M and network size N on structural controllability are examined. For local-world networks with sparse topological configuration, compared to network size, local-world size can induce stronger influence on controllability, however, for dense networks, controllability is greatly affected by network size and local-world effect can be neglected. Secondly, relationships between controllability and topological properties are analyzed. Lastly, the robustness of local-world networks under targeted attacks regarding structural controllability is discussed. These results can help to deepen the understanding of structural complexity and connectivity patterns of complex systems. - Highlights: • Structural controllability of a class of local-world networks is investigated. • For sparse local-world networks, compared to network size, local-world size can bring stronger influence on controllability. • For dense networks, controllability is greatly affected by network size and the effect of local-world size can be neglected. • Structural controllability against targeted node attacks is discussed.

Towards structural controllability of local-world networks

Energy Technology Data Exchange (ETDEWEB)

Sun, Shiwen, E-mail: sunsw80@126.com [Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384 (China); Key Laboratory of Computer Vision and System (Tianjin University of Technology), Ministry of Education, Tianjin 300384 (China); Ma, Yilin; Wu, Yafang; Wang, Li; Xia, Chengyi [Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384 (China); Key Laboratory of Computer Vision and System (Tianjin University of Technology), Ministry of Education, Tianjin 300384 (China)

2016-05-20

Controlling complex networks is of vital importance in science and engineering. Meanwhile, local-world effect is an important ingredient which should be taken into consideration in the complete description of real-world complex systems. In this letter, structural controllability of a class of local-world networks is investigated. Through extensive numerical simulations, firstly, effects of local world size M and network size N on structural controllability are examined. For local-world networks with sparse topological configuration, compared to network size, local-world size can induce stronger influence on controllability, however, for dense networks, controllability is greatly affected by network size and local-world effect can be neglected. Secondly, relationships between controllability and topological properties are analyzed. Lastly, the robustness of local-world networks under targeted attacks regarding structural controllability is discussed. These results can help to deepen the understanding of structural complexity and connectivity patterns of complex systems. - Highlights: • Structural controllability of a class of local-world networks is investigated. • For sparse local-world networks, compared to network size, local-world size can bring stronger influence on controllability. • For dense networks, controllability is greatly affected by network size and the effect of local-world size can be neglected. • Structural controllability against targeted node attacks is discussed.

Label-Driven Learning Framework: Towards More Accurate Bayesian Network Classifiers through Discrimination of High-Confidence Labels

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.

Do Convolutional Neural Networks Learn Class Hierarchy?

Science.gov (United States)

Bilal, Alsallakh; Jourabloo, Amin; Ye, Mao; Liu, Xiaoming; Ren, Liu

2018-01-01

Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class confusion patterns follow a hierarchical structure over the classes. We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data. We found that this hierarchy not only dictates the confusion patterns between the classes, it furthermore dictates the learning behavior of CNNs. In particular, the early layers in these networks develop feature detectors that can separate high-level groups of classes quite well, even after a few training epochs. In contrast, the latter layers require substantially more epochs to develop specialized feature detectors that can separate individual classes. We demonstrate how these insights are key to significant improvement in accuracy by designing hierarchy-aware CNNs that accelerate model convergence and alleviate overfitting. We further demonstrate how our methods help in identifying various quality issues in the training data.

Learning of N-layers neural network

Directory of Open Access Journals (Sweden)

Vladimír Konečný

2005-01-01

Full Text Available In the last decade we can observe increasing number of applications based on the Artificial Intelligence that are designed to solve problems from different areas of human activity. The reason why there is so much interest in these technologies is that the classical way of solutions does not exist or these technologies are not suitable because of their robustness. They are often used in applications like Business Intelligence that enable to obtain useful information for high-quality decision-making and to increase competitive advantage.One of the most widespread tools for the Artificial Intelligence are the artificial neural networks. Their high advantage is relative simplicity and the possibility of self-learning based on set of pattern situations.For the learning phase is the most commonly used algorithm back-propagation error (BPE. The base of BPE is the method minima of error function representing the sum of squared errors on outputs of neural net, for all patterns of the learning set. However, while performing BPE and in the first usage, we can find out that it is necessary to complete the handling of the learning factor by suitable method. The stability of the learning process and the rate of convergence depend on the selected method. In the article there are derived two functions: one function for the learning process management by the relative great error function value and the second function when the value of error function approximates to global minimum.The aim of the article is to introduce the BPE algorithm in compact matrix form for multilayer neural networks, the derivation of the learning factor handling method and the presentation of the results.

The Practices of Student Network as Cooperative Learning in Ethiopia

Science.gov (United States)

Reda, Weldemariam Nigusse; Hagos, Girmay Tsegay

2015-01-01

Student network is a teaching strategy introduced as cooperative learning to all educational levels above the upper primary schools (grade 5 and above) in Ethiopia. The study was, therefore, aimed at investigating to what extent the student network in Ethiopia is actually practiced in line with the principles of cooperative learning. Consequently,…

"Getting Practical" and the National Network of Science Learning Centres

Science.gov (United States)

Chapman, Georgina; Langley, Mark; Skilling, Gus; Walker, John

2011-01-01

The national network of Science Learning Centres is a co-ordinating partner in the Getting Practical--Improving Practical Work in Science programme. The principle of training provision for the "Getting Practical" programme is a cascade model. Regional trainers employed by the national network of Science Learning Centres trained the cohort of local…

Deep learning and the electronic structure problem

Science.gov (United States)

Mills, Kyle; Spanner, Michael; Tamblyn, Isaac

In the past decade, the fields of artificial intelligence and computer vision have progressed remarkably. Supported by the enthusiasm of large tech companies, as well as significant hardware advances and the utilization of graphical processing units to accelerate computations, deep neural networks (DNN) are gaining momentum as a robust choice for many diverse machine learning applications. We have demonstrated the ability of a DNN to solve a quantum mechanical eigenvalue equation directly, without the need to compute a wavefunction, and without knowledge of the underlying physics. We have trained a convolutional neural network to predict the total energy of an electron in a confining, 2-dimensional electrostatic potential. We numerically solved the one-electron Schrödinger equation for millions of electrostatic potentials, and used this as training data for our neural network. Four classes of potentials were assessed: the canonical cases of the harmonic oscillator and infinite well, and two types of randomly generated potentials for which no analytic solution is known. We compare the performance of the neural network and consider how these results could lead to future advances in electronic structure theory.

Mimicking Nature´s way of organizing in industry: a network learning perspective

DEFF Research Database (Denmark)

Ulhøi, John Parm; Madsen, Henning

to reconsider organisational learning as being both an internal as well as an external phenomenon. By bringing network learning into an existing interorganisational setting (such as industrial ecology) new potentials for increased learning emerge for the participating companies. The concept of network learning...

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks.

Science.gov (United States)

Zhao, Rui; Yan, Ruqiang; Wang, Jinjiang; Mao, Kezhi

2017-01-30

In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks

Directory of Open Access Journals (Sweden)

Rui Zhao

2017-01-01

Full Text Available In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

Finite time convergent learning law for continuous neural networks.

Science.gov (United States)

Chairez, Isaac

2014-02-01

This paper addresses the design of a discontinuous finite time convergent learning law for neural networks with continuous dynamics. The neural network was used here to obtain a non-parametric model for uncertain systems described by a set of ordinary differential equations. The source of uncertainties was the presence of some external perturbations and poor knowledge of the nonlinear function describing the system dynamics. A new adaptive algorithm based on discontinuous algorithms was used to adjust the weights of the neural network. The adaptive algorithm was derived by means of a non-standard Lyapunov function that is lower semi-continuous and differentiable in almost the whole space. A compensator term was included in the identifier to reject some specific perturbations using a nonlinear robust algorithm. Two numerical examples demonstrated the improvements achieved by the learning algorithm introduced in this paper compared to classical schemes with continuous learning methods. The first one dealt with a benchmark problem used in the paper to explain how the discontinuous learning law works. The second one used the methane production model to show the benefits in engineering applications of the learning law proposed in this paper. Copyright © 2013 Elsevier Ltd. All rights reserved.

Biologically-inspired On-chip Learning in Pulsed Neural Networks

DEFF Research Database (Denmark)

Lehmann, Torsten; Woodburn, Robin

1999-01-01

Self-learning chips to implement many popular ANN (artificial neural network) algorithms are very difficult to design. We explain why this is so and say what lessons previous work teaches us in the design of self-learning systems. We offer a contribution to the "biologically-inspired" approach......, explaining what we mean by this term and providing an example of a robust, self-learning design that can solve simple classical-conditioning tasks, We give details of the design of individual circuits to perform component functions, which can then be combined into a network to solve the task. We argue...

Exploring biological network structure with clustered random networks

Directory of Open Access Journals (Sweden)

Bansal Shweta

2009-12-01

Full Text Available Abstract Background Complex biological systems are often modeled as networks of interacting units. Networks of biochemical interactions among proteins, epidemiological contacts among hosts, and trophic interactions in ecosystems, to name a few, have provided useful insights into the dynamical processes that shape and traverse these systems. The degrees of nodes (numbers of interactions and the extent of clustering (the tendency for a set of three nodes to be interconnected are two of many well-studied network properties that can fundamentally shape a system. Disentangling the interdependent effects of the various network properties, however, can be difficult. Simple network models can help us quantify the structure of empirical networked systems and understand the impact of various topological properties on dynamics. Results Here we develop and implement a new Markov chain simulation algorithm to generate simple, connected random graphs that have a specified degree sequence and level of clustering, but are random in all other respects. The implementation of the algorithm (ClustRNet: Clustered Random Networks provides the generation of random graphs optimized according to a local or global, and relative or absolute measure of clustering. We compare our algorithm to other similar methods and show that ours more successfully produces desired network characteristics. Finding appropriate null models is crucial in bioinformatics research, and is often difficult, particularly for biological networks. As we demonstrate, the networks generated by ClustRNet can serve as random controls when investigating the impacts of complex network features beyond the byproduct of degree and clustering in empirical networks. Conclusion ClustRNet generates ensembles of graphs of specified edge structure and clustering. These graphs allow for systematic study of the impacts of connectivity and redundancies on network function and dynamics. This process is a key step in

Personal Learning Network Clusters: A Comparison between Mathematics and Computer Science Students

Science.gov (United States)

Harding, Ansie; Engelbrecht, Johann

2015-01-01

"Personal learning environments" (PLEs) and "personal learning networks" (PLNs) are well-known concepts. A personal learning network "cluster" is a small group of people who regularly interact academically and whose PLNs have a non-empty intersection that includes all the other members. At university level PLN…

Dialogue, Language and Identity: Critical Issues for Networked Management Learning

Science.gov (United States)

Ferreday, Debra; Hodgson, Vivien; Jones, Chris

2006-01-01

This paper draws on the work of Mikhail Bakhtin and Norman Fairclough to show how dialogue is central to the construction of identity in networked management learning. The paper is based on a case study of a networked management learning course in higher education and attempts to illustrate how participants negotiate issues of difference,…

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

Science.gov (United States)

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Machine learning and complex-network for personalized and systems biomedicine

KAUST Repository

Cannistraci, Carlo Vittorio

2016-01-27

The talk will begin with an introduction on using machine learning to discover hidden information and unexpected patterns in large biomedical datasets. Then, recent results on the use of complex network theory in biomedicine and neuroscience will be discussed. In particular, metagenomics and metabolomics data, approaches for drug-target repositioning, functional/structural MR connectomes and gut-brain axis data will be presented. The conclusion will outline the novel and exciting perspectives offered by the translation of these methods from systems biology to systems medicine.

Practice and Learning: Spatiotemporal Differences in Thalamo-Cortical-Cerebellar Networks Engagement across Learning Phases in Schizophrenia.

Science.gov (United States)

Korostil, Michele; Remington, Gary; McIntosh, Anthony Randal

2016-01-01

Understanding how practice mediates the transition of brain-behavior networks between early and later stages of learning is constrained by the common approach to analysis of fMRI data. Prior imaging studies have mostly relied on a single scan, and parametric, task-related analyses. Our experiment incorporates a multisession fMRI lexicon-learning experiment with multivariate, whole-brain analysis to further knowledge of the distributed networks supporting practice-related learning in schizophrenia (SZ). Participants with SZ were compared with healthy control (HC) participants as they learned a novel lexicon during two fMRI scans over a several day period. All participants were trained to equal task proficiency prior to scanning. Behavioral-Partial Least Squares, a multivariate analytic approach, was used to analyze the imaging data. Permutation testing was used to determine statistical significance and bootstrap resampling to determine the reliability of the findings. With practice, HC participants transitioned to a brain-accuracy network incorporating dorsostriatal regions in late-learning stages. The SZ participants did not transition to this pattern despite comparable behavioral results. Instead, successful learners with SZ were differentiated primarily on the basis of greater engagement of perceptual and perceptual-integration brain regions. There is a different spatiotemporal unfolding of brain-learning relationships in SZ. In SZ, given the same amount of practice, the movement from networks suggestive of effortful learning toward subcortically driven procedural one differs from HC participants. Learning performance in SZ is driven by varying levels of engagement in perceptual regions, which suggests perception itself is impaired and may impact downstream, "higher level" cognition.

Prefrontal Cortex Networks Shift from External to Internal Modes during Learning

Science.gov (United States)

Brincat, Scott L.

2016-01-01

As we learn about items in our environment, their neural representations become increasingly enriched with our acquired knowledge. But there is little understanding of how network dynamics and neural processing related to external information changes as it becomes laden with “internal” memories. We sampled spiking and local field potential activity simultaneously from multiple sites in the lateral prefrontal cortex (PFC) and the hippocampus (HPC)—regions critical for sensory associations—of monkeys performing an object paired-associate learning task. We found that in the PFC, evoked potentials to, and neural information about, external sensory stimulation decreased while induced beta-band (∼11–27 Hz) oscillatory power and synchrony associated with “top-down” or internal processing increased. By contrast, the HPC showed little evidence of learning-related changes in either spiking activity or network dynamics. The results suggest that during associative learning, PFC networks shift their resources from external to internal processing. SIGNIFICANCE STATEMENT As we learn about items in our environment, their representations in our brain become increasingly enriched with our acquired “top-down” knowledge. We found that in the prefrontal cortex, but not the hippocampus, processing of external sensory inputs decreased while internal network dynamics related to top-down processing increased. The results suggest that during learning, prefrontal cortex networks shift their resources from external (sensory) to internal (memory) processing. PMID:27629722

Network Enabled - Unresolved Residual Analysis and Learning (NEURAL)

Science.gov (United States)

Temple, D.; Poole, M.; Camp, M.

Since the advent of modern computational capacity, machine learning algorithms and techniques have served as a method through which to solve numerous challenging problems. However, for machine learning methods to be effective and robust, sufficient data sets must be available; specifically, in the space domain, these are generally difficult to acquire. Rapidly evolving commercial space-situational awareness companies boast the capability to collect hundreds of thousands nightly observations of resident space objects (RSOs) using a ground-based optical sensor network. This provides the ability to maintain custody of and characterize thousands of objects persistently. With this information available, novel deep learning techniques can be implemented. The technique discussed in this paper utilizes deep learning to make distinctions between nightly data collects with and without maneuvers. Implementation of these techniques will allow the data collected from optical ground-based networks to enable well informed and timely the space domain decision making.

An examination of a reciprocal relationship between network governance and network structure

DEFF Research Database (Denmark)

Bergenholtz, Carsten; Goduscheit, René Chester

2011-01-01

In the present article, we examine the network structure and governance of inter-organisational innovation networks over time. Network governance refers to the issue of how to manage and coordinate the relational activities and processes in the network while research on network structure deals...

U.S. stock market interaction network as learned by the Boltzmann machine

Science.gov (United States)

Borysov, Stanislav S.; Roudi, Yasser; Balatsky, Alexander V.

2015-12-01

We study historical dynamics of joint equilibrium distribution of stock returns in the U.S. stock market using the Boltzmann distribution model being parametrized by external fields and pairwise couplings. Within Boltzmann learning framework for statistical inference, we analyze historical behavior of the parameters inferred using exact and approximate learning algorithms. Since the model and inference methods require use of binary variables, effect of this mapping of continuous returns to the discrete domain is studied. The presented results show that binarization preserves the correlation structure of the market. Properties of distributions of external fields and couplings as well as the market interaction network and industry sector clustering structure are studied for different historical dates and moving window sizes. We demonstrate that the observed positive heavy tail in distribution of couplings is related to the sparse clustering structure of the market. We also show that discrepancies between the model's parameters might be used as a precursor of financial instabilities.

Learners’ Views Regarding the Use of Social Networking Sites in Distance Learning

Directory of Open Access Journals (Sweden)

Büşra Özmen

2014-09-01

Full Text Available In this study, it was aimed to examine the use of learning management systems supported by social networking sites in distance education and to determine the views of learners regarding these platforms. The study group of this study, which uses a qualitative research approach, consists of 15 undergraduate students who resumed their education in Turkey. The data were gathered via a semi-structured interview form which consists of open-ended questions. Content analysis was used in the analysis of the data. According to the results of the study, it has been revealed within the scope of the course that the students have positive attitudes towards the use of social networking sites and distance education applications and these applications have positively affected the quality of communication between instructors and students. Furthermore, it was seen that the students made comments relating to the interesting aspects of the applications and the difference between distance education and face-to-face learning.

Supervised dictionary learning for inferring concurrent brain networks.

Science.gov (United States)

Zhao, Shijie; Han, Junwei; Lv, Jinglei; Jiang, Xi; Hu, Xintao; Zhao, Yu; Ge, Bao; Guo, Lei; Liu, Tianming

2015-10-01

Task-based fMRI (tfMRI) has been widely used to explore functional brain networks via predefined stimulus paradigm in the fMRI scan. Traditionally, the general linear model (GLM) has been a dominant approach to detect task-evoked networks. However, GLM focuses on task-evoked or event-evoked brain responses and possibly ignores the intrinsic brain functions. In comparison, dictionary learning and sparse coding methods have attracted much attention recently, and these methods have shown the promise of automatically and systematically decomposing fMRI signals into meaningful task-evoked and intrinsic concurrent networks. Nevertheless, two notable limitations of current data-driven dictionary learning method are that the prior knowledge of task paradigm is not sufficiently utilized and that the establishment of correspondences among dictionary atoms in different brains have been challenging. In this paper, we propose a novel supervised dictionary learning and sparse coding method for inferring functional networks from tfMRI data, which takes both of the advantages of model-driven method and data-driven method. The basic idea is to fix the task stimulus curves as predefined model-driven dictionary atoms and only optimize the other portion of data-driven dictionary atoms. Application of this novel methodology on the publicly available human connectome project (HCP) tfMRI datasets has achieved promising results.

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

Science.gov (United States)

Gong, Maoguo; Liu, Jia; Li, Hao; Cai, Qing; Su, Linzhi

2015-12-01

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

Celebrating the Tenth Networked Learning Conference: Looking Back and Moving Forward

DEFF Research Database (Denmark)

de Laat, Maarten; Ryberg, Thomas

2018-01-01

conferences with the aim to describe some general trends and developments in networked learning research as they emerge and fade out over the years. In order to do so the authors use the proceedings of each networked learning conference (from 1998 till 2016) as a compiled dataset. This dataset forms a text...... corpus that has been analysed with Voyant tools (Sinclair and Rockwell 2016) specifically designed for analysing digital texts. Voyant tools are used to generate a set of word clouds (Cirrus) in order to visualise networked learning research-related terms that feature most frequently in each set...

Assessment of Learning in Digital Interactive Social Networks: A Learning Analytics Approach

Science.gov (United States)

Wilson, Mark; Gochyyev, Perman; Scalise, Kathleen

2016-01-01

This paper summarizes initial field-test results from data analytics used in the work of the Assessment and Teaching of 21st Century Skills (ATC21S) project, on the "ICT Literacy--Learning in digital networks" learning progression. This project, sponsored by Cisco, Intel and Microsoft, aims to help educators around the world enable…

Mirrored STDP Implements Autoencoder Learning in a Network of Spiking Neurons.

Science.gov (United States)

Burbank, Kendra S

2015-12-01

The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be stacked to learn increasingly abstract representations. Several computational neuroscience models of sensory areas, including Olshausen & Field's Sparse Coding algorithm, can be seen as autoencoder variants, and autoencoders have seen extensive use in the machine learning community. Despite their power and versatility, autoencoders have been difficult to implement in a biologically realistic fashion. The challenges include their need to calculate differences between two neuronal activities and their requirement for learning rules which lead to identical changes at feedforward and feedback connections. Here, we study a biologically realistic network of integrate-and-fire neurons with anatomical connectivity and synaptic plasticity that closely matches that observed in cortical sensory areas. Our choice of synaptic plasticity rules is inspired by recent experimental and theoretical results suggesting that learning at feedback connections may have a different form from learning at feedforward connections, and our results depend critically on this novel choice of plasticity rules. Specifically, we propose that plasticity rules at feedforward versus feedback connections are temporally opposed versions of spike-timing dependent plasticity (STDP), leading to a symmetric combined rule we call Mirrored STDP (mSTDP). We show that with mSTDP, our network follows a learning rule that approximately minimizes an autoencoder loss function. When trained with whitened natural image patches, the learned synaptic weights resemble the receptive fields seen in V1. Our results use realistic synaptic plasticity rules to show that the powerful autoencoder learning algorithm could be within the reach of real biological networks.

Conceptualizing the e-Learning Assessment Domain using an Ontology Network

Directory of Open Access Journals (Sweden)

Lucía Romero

2012-09-01

Full Text Available During the last year, approaches that use ontologies, the backbone of the Semantic Web technologies, for different purposes in the assessment domain of e-Learning have emerged. One of these purposes is the use of ontologies as a mean of providing a structure to guide the automated design of assessments. The most of the approaches that deal with this problem have proposed individual ontologies that model only a part of the assessment domain. The main contribution of this paper is an ontology network, called AONet, that conceptualizes the e-assessment domain with the aim of supporting the semi-automatic generation of it. The main advantage of this network is that it is enriched with rules for considering not only technical aspects of an assessment but also pedagogic

Artificial neuron-glia networks learning approach based on cooperative coevolution.

Science.gov (United States)

Mesejo, Pablo; Ibáñez, Oscar; Fernández-Blanco, Enrique; Cedrón, Francisco; Pazos, Alejandro; Porto-Pazos, Ana B

2015-06-01

Artificial Neuron-Glia Networks (ANGNs) are a novel bio-inspired machine learning approach. They extend classical Artificial Neural Networks (ANNs) by incorporating recent findings and suppositions about the way information is processed by neural and astrocytic networks in the most evolved living organisms. Although ANGNs are not a consolidated method, their performance against the traditional approach, i.e. without artificial astrocytes, was already demonstrated on classification problems. However, the corresponding learning algorithms developed so far strongly depends on a set of glial parameters which are manually tuned for each specific problem. As a consequence, previous experimental tests have to be done in order to determine an adequate set of values, making such manual parameter configuration time-consuming, error-prone, biased and problem dependent. Thus, in this paper, we propose a novel learning approach for ANGNs that fully automates the learning process, and gives the possibility of testing any kind of reasonable parameter configuration for each specific problem. This new learning algorithm, based on coevolutionary genetic algorithms, is able to properly learn all the ANGNs parameters. Its performance is tested on five classification problems achieving significantly better results than ANGN and competitive results with ANN approaches.

A smart-pixel holographic competitive learning network

Science.gov (United States)

Slagle, Timothy Michael

Neural networks are adaptive classifiers which modify their decision boundaries based on feedback from externally- or internally-generated error signals. Optics is an attractive technology for neural network implementation because it offers the possibility of parallel, nearly instantaneous computation of the weighted neuron inputs by the propagation of light through the optical system. Using current optical device technology, system performance levels of 3 × 1011 connection updates per second can be achieved. This thesis presents an architecture for an optical competitive learning network which offers advantages over previous optical implementations, including smart-pixel-based optical neurons, phase- conjugate self-alignment of a single neuron plane, and high-density, parallel-access weight storage, interconnection, and learning in a volume hologram. The competitive learning algorithm with modifications for optical implementation is described, and algorithm simulations are performed for an example problem. The optical competitive learning architecture is then introduced. The optical system is simulated using the ``beamprop'' algorithm at the level of light propagating through the system components, and results showing competitive learning operation in agreement with the algorithm simulations are presented. The optical competitive learning requires a non-linear, non-local ``winner-take-all'' (WTA) neuron function. Custom-designed smart-pixel WTA neuron arrays were fabricated using CMOS VLSI/liquid crystal technology. Results of laboratory tests of the WTA arrays' switching characteristics, time response, and uniformity are then presented. The system uses a phase-conjugate mirror to write the self-aligning interconnection weight holograms, and energy gain is required from the reflection to minimize erasure of the existing weights. An experimental system for characterizing the PCM response is described. Useful gains of 20 were obtained with a polarization

Learning in Networks for Sustainable Development

NARCIS (Netherlands)

Lansu, Angelique; Boon, Jo; Sloep, Peter; Van Dam-Mieras, Rietje

2010-01-01

The didactic model of remote internships described in this study provides the flexibility needed to support networked learners, i.e. to facilitate the development and subsequent assessment of their competences. The heterogeneity of the participants (students, employers, tutors) in the learning

Sentiment analysis: a comparison of deep learning neural network algorithm with SVM and naϊve Bayes for Indonesian text

Science.gov (United States)

Calvin Frans Mariel, Wahyu; Mariyah, Siti; Pramana, Setia

2018-03-01

Deep learning is a new era of machine learning techniques that essentially imitate the structure and function of the human brain. It is a development of deeper Artificial Neural Network (ANN) that uses more than one hidden layer. Deep Learning Neural Network has a great ability on recognizing patterns from various data types such as picture, audio, text, and many more. In this paper, the authors tries to measure that algorithm’s ability by applying it into the text classification. The classification task herein is done by considering the content of sentiment in a text which is also called as sentiment analysis. By using several combinations of text preprocessing and feature extraction techniques, we aim to compare the precise modelling results of Deep Learning Neural Network with the other two commonly used algorithms, the Naϊve Bayes and Support Vector Machine (SVM). This algorithm comparison uses Indonesian text data with balanced and unbalanced sentiment composition. Based on the experimental simulation, Deep Learning Neural Network clearly outperforms the Naϊve Bayes and SVM and offers a better F-1 Score while for the best feature extraction technique which improves that modelling result is Bigram.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

Science.gov (United States)

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-04-10

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Relabeling exchange method (REM) for learning in neural networks

Science.gov (United States)

Wu, Wen; Mammone, Richard J.

1994-02-01

The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

Robustness and structure of complex networks

Science.gov (United States)

Shao, Shuai

This dissertation covers the two major parts of my PhD research on statistical physics and complex networks: i) modeling a new type of attack -- localized attack, and investigating robustness of complex networks under this type of attack; ii) discovering the clustering structure in complex networks and its influence on the robustness of coupled networks. Complex networks appear in every aspect of our daily life and are widely studied in Physics, Mathematics, Biology, and Computer Science. One important property of complex networks is their robustness under attacks, which depends crucially on the nature of attacks and the structure of the networks themselves. Previous studies have focused on two types of attack: random attack and targeted attack, which, however, are insufficient to describe many real-world damages. Here we propose a new type of attack -- localized attack, and study the robustness of complex networks under this type of attack, both analytically and via simulation. On the other hand, we also study the clustering structure in the network, and its influence on the robustness of a complex network system. In the first part, we propose a theoretical framework to study the robustness of complex networks under localized attack based on percolation theory and generating function method. We investigate the percolation properties, including the critical threshold of the phase transition pc and the size of the giant component Pinfinity. We compare localized attack with random attack and find that while random regular (RR) networks are more robust against localized attack, Erdoḧs-Renyi (ER) networks are equally robust under both types of attacks. As for scale-free (SF) networks, their robustness depends crucially on the degree exponent lambda. The simulation results show perfect agreement with theoretical predictions. We also test our model on two real-world networks: a peer-to-peer computer network and an airline network, and find that the real-world networks

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.

Extraction of business relationships in supply networks using statistical learning theory.

Science.gov (United States)

Zuo, Yi; Kajikawa, Yuya; Mori, Junichiro

2016-06-01

Supply chain management represents one of the most important scientific streams of operations research. The supply of energy, materials, products, and services involves millions of transactions conducted among national and local business enterprises. To deliver efficient and effective support for supply chain design and management, structural analyses and predictive models of customer-supplier relationships are expected to clarify current enterprise business conditions and to help enterprises identify innovative business partners for future success. This article presents the outcomes of a recent structural investigation concerning a supply network in the central area of Japan. We investigated the effectiveness of statistical learning theory to express the individual differences of a supply chain of enterprises within a certain business community using social network analysis. In the experiments, we employ support vector machine to train a customer-supplier relationship model on one of the main communities extracted from a supply network in the central area of Japan. The prediction results reveal an F-value of approximately 70% when the model is built by using network-based features, and an F-value of approximately 77% when the model is built by using attribute-based features. When we build the model based on both, F-values are improved to approximately 82%. The results of this research can help to dispel the implicit design space concerning customer-supplier relationships, which can be explored and refined from detailed topological information provided by network structures rather than from traditional and attribute-related enterprise profiles. We also investigate and discuss differences in the predictive accuracy of the model for different sizes of enterprises and types of business communities.

Extraction of business relationships in supply networks using statistical learning theory

Directory of Open Access Journals (Sweden)

Yi Zuo

2016-06-01

Full Text Available Supply chain management represents one of the most important scientific streams of operations research. The supply of energy, materials, products, and services involves millions of transactions conducted among national and local business enterprises. To deliver efficient and effective support for supply chain design and management, structural analyses and predictive models of customer–supplier relationships are expected to clarify current enterprise business conditions and to help enterprises identify innovative business partners for future success. This article presents the outcomes of a recent structural investigation concerning a supply network in the central area of Japan. We investigated the effectiveness of statistical learning theory to express the individual differences of a supply chain of enterprises within a certain business community using social network analysis. In the experiments, we employ support vector machine to train a customer–supplier relationship model on one of the main communities extracted from a supply network in the central area of Japan. The prediction results reveal an F-value of approximately 70% when the model is built by using network-based features, and an F-value of approximately 77% when the model is built by using attribute-based features. When we build the model based on both, F-values are improved to approximately 82%. The results of this research can help to dispel the implicit design space concerning customer–supplier relationships, which can be explored and refined from detailed topological information provided by network structures rather than from traditional and attribute-related enterprise profiles. We also investigate and discuss differences in the predictive accuracy of the model for different sizes of enterprises and types of business communities.

Factors that influence cooperation in networks for innovation and learning

NARCIS (Netherlands)

Sie, Rory; Bitter-Rijpkema, Marlies; Stoyanov, Slavi; Sloep, Peter

2018-01-01

Networked cooperation fails if the available partnerships remain opaque. A literature review and Delphi study uncovered the elements of a fruitful partnership. They relate to personality, diversity, cooperation, and management. Innovation networks and learning networks share the same cooperative

STRUCTURE AND COOPTATION IN ORGANIZATION NETWORK

Directory of Open Access Journals (Sweden)

Valéria Riscarolli

2007-10-01

Full Text Available Business executive are rethinking business concept, based on horizontalization principles. As so, most organizational functions are outsourced, leading the enterprise to build business through a network of organizations. Here we study the case of Cia Hering’s network of organizations, a leader in knit apparel segment in Latin America (IEMI, 2004, looking at the network’s structure and levels of cooptation. A theoretical model was used using Quinn et al. (2001 “sun ray” network structure as basis to analyze the case study. Main results indicate higher degree of structural conformity, but incipient degree of coopetation in the network.

Nuclear power plant monitoring using real-time learning neural network

International Nuclear Information System (INIS)

Nabeshima, Kunihiko; Tuerkcan, E.; Ciftcioglu, O.

1994-01-01

In the present research, artificial neural network (ANN) with real-time adaptive learning is developed for the plant wide monitoring of Borssele Nuclear Power Plant (NPP). Adaptive ANN learning capability is integrated to the monitoring system so that robust and sensitive on-line monitoring is achieved in real-time environment. The major advantages provided by ANN are that system modelling is formed by means of measurement information obtained from a multi-output process system, explicit modelling is not required and the modelling is not restricted to linear systems. Also ANN can respond very fast to anomalous operational conditions. The real-time ANN learning methodology with adaptive real-time monitoring capability is described below for the wide-range and plant-wide data from an operating nuclear power plant. The layered neural network with error backpropagation algorithm for learning has three layers. The network type is auto-associative, inputs and outputs are exactly the same, using 12 plant signals. (author)

Implementation of a Framework for Collaborative Social Networks in E-Learning

Science.gov (United States)

Maglajlic, Seid

2016-01-01

This paper describes the implementation of a framework for the construction and utilization of social networks in ELearning. These social networks aim to enhance collaboration between all E-Learning participants (i.e. both traineeto-trainee and trainee-to-tutor communication are targeted). E-Learning systems that include a so-called "social…

Learning and innovative elements of strategy adoption rules expand cooperative network topologies.

Science.gov (United States)

Wang, Shijun; Szalay, Máté S; Zhang, Changshui; Csermely, Peter

2008-04-09

Cooperation plays a key role in the evolution of complex systems. However, the level of cooperation extensively varies with the topology of agent networks in the widely used models of repeated games. Here we show that cooperation remains rather stable by applying the reinforcement learning strategy adoption rule, Q-learning on a variety of random, regular, small-word, scale-free and modular network models in repeated, multi-agent Prisoner's Dilemma and Hawk-Dove games. Furthermore, we found that using the above model systems other long-term learning strategy adoption rules also promote cooperation, while introducing a low level of noise (as a model of innovation) to the strategy adoption rules makes the level of cooperation less dependent on the actual network topology. Our results demonstrate that long-term learning and random elements in the strategy adoption rules, when acting together, extend the range of network topologies enabling the development of cooperation at a wider range of costs and temptations. These results suggest that a balanced duo of learning and innovation may help to preserve cooperation during the re-organization of real-world networks, and may play a prominent role in the evolution of self-organizing, complex systems.

SISL and SIRL: Two knowledge dissemination models with leader nodes on cooperative learning networks

Science.gov (United States)

Li, Jingjing; Zhang, Yumei; Man, Jiayu; Zhou, Yun; Wu, Xiaojun

2017-02-01

Cooperative learning is one of the most effective teaching methods, which has been widely used. Students' mutual contact forms a cooperative learning network in this process. Our previous research demonstrated that the cooperative learning network has complex characteristics. This study aims to investigating the dynamic spreading process of the knowledge in the cooperative learning network and the inspiration of leaders in this process. To this end, complex network transmission dynamics theory is utilized to construct the knowledge dissemination model of a cooperative learning network. Based on the existing epidemic models, we propose a new susceptible-infected-susceptible-leader (SISL) model that considers both students' forgetting and leaders' inspiration, and a susceptible-infected-removed-leader (SIRL) model that considers students' interest in spreading and leaders' inspiration. The spreading threshold λcand its impact factors are analyzed. Then, numerical simulation and analysis are delivered to reveal the dynamic transmission mechanism of knowledge and leaders' role. This work is of great significance to cooperative learning theory and teaching practice. It also enriches the theory of complex network transmission dynamics.

An evolving network model with community structure

International Nuclear Information System (INIS)

Li Chunguang; Maini, Philip K

2005-01-01

Many social and biological networks consist of communities-groups of nodes within which connections are dense, but between which connections are sparser. Recently, there has been considerable interest in designing algorithms for detecting community structures in real-world complex networks. In this paper, we propose an evolving network model which exhibits community structure. The network model is based on the inner-community preferential attachment and inter-community preferential attachment mechanisms. The degree distributions of this network model are analysed based on a mean-field method. Theoretical results and numerical simulations indicate that this network model has community structure and scale-free properties

Social Networks and Performance in Distributed Learning Communities

Science.gov (United States)

Cadima, Rita; Ojeda, Jordi; Monguet, Josep M.

2012-01-01

Social networks play an essential role in learning environments as a key channel for knowledge sharing and students' support. In distributed learning communities, knowledge sharing does not occur as spontaneously as when a working group shares the same physical space; knowledge sharing depends even more on student informal connections. In this…

Continual and One-Shot Learning Through Neural Networks with Dynamic External Memory

DEFF Research Database (Denmark)

Lüders, Benno; Schläger, Mikkel; Korach, Aleksandra

2017-01-01

it easier to find unused memory location and therefor facilitates the evolution of continual learning networks. Our results suggest that augmenting evolving networks with an external memory component is not only a viable mechanism for adaptive behaviors in neuroevolution but also allows these networks...... a new task is learned. This paper takes a step in overcoming this limitation by building on the recently proposed Evolving Neural Turing Machine (ENTM) approach. In the ENTM, neural networks are augmented with an external memory component that they can write to and read from, which allows them to store...... associations quickly and over long periods of time. The results in this paper demonstrate that the ENTM is able to perform one-shot learning in reinforcement learning tasks without catastrophic forgetting of previously stored associations. Additionally, we introduce a new ENTM default jump mechanism that makes...

Immunization of networks with community structure

International Nuclear Information System (INIS)

Masuda, Naoki

2009-01-01

In this study, an efficient method to immunize modular networks (i.e. networks with community structure) is proposed. The immunization of networks aims at fragmenting networks into small parts with a small number of removed nodes. Its applications include prevention of epidemic spreading, protection against intentional attacks on networks, and conservation of ecosystems. Although preferential immunization of hubs is efficient, good immunization strategies for modular networks have not been established. On the basis of an immunization strategy based on eigenvector centrality, we develop an analytical framework for immunizing modular networks. To this end, we quantify the contribution of each node to the connectivity in a coarse-grained network among modules. We verify the effectiveness of the proposed method by applying it to model and real networks with modular structure.

The network structure of human personality according to the NEO-PI-R: matching network community structure to factor structure.

Directory of Open Access Journals (Sweden)

Rutger Goekoop

Full Text Available INTRODUCTION: Human personality is described preferentially in terms of factors (dimensions found using factor analysis. An alternative and highly related method is network analysis, which may have several advantages over factor analytic methods. AIM: To directly compare the ability of network community detection (NCD and principal component factor analysis (PCA to examine modularity in multidimensional datasets such as the neuroticism-extraversion-openness personality inventory revised (NEO-PI-R. METHODS: 434 healthy subjects were tested on the NEO-PI-R. PCA was performed to extract factor structures (FS of the current dataset using both item scores and facet scores. Correlational network graphs were constructed from univariate correlation matrices of interactions between both items and facets. These networks were pruned in a link-by-link fashion while calculating the network community structure (NCS of each resulting network using the Wakita Tsurumi clustering algorithm. NCSs were matched against FS and networks of best matches were kept for further analysis. RESULTS: At facet level, NCS showed a best match (96.2% with a 'confirmatory' 5-FS. At item level, NCS showed a best match (80% with the standard 5-FS and involved a total of 6 network clusters. Lesser matches were found with 'confirmatory' 5-FS and 'exploratory' 6-FS of the current dataset. Network analysis did not identify facets as a separate level of organization in between items and clusters. A small-world network structure was found in both item- and facet level networks. CONCLUSION: We present the first optimized network graph of personality traits according to the NEO-PI-R: a 'Personality Web'. Such a web may represent the possible routes that subjects can take during personality development. NCD outperforms PCA by producing plausible modularity at item level in non-standard datasets, and can identify the key roles of individual items and clusters in the network.

Students' Personal Networks in Virtual and Personal Learning Environments: A Case Study in Higher Education Using Learning Analytics Approach

Science.gov (United States)

Casquero, Oskar; Ovelar, Ramón; Romo, Jesús; Benito, Manuel; Alberdi, Mikel

2016-01-01

The main objective of this paper is to analyse the effect of the affordances of a virtual learning environment and a personal learning environment (PLE) in the configuration of the students' personal networks in a higher education context. The results are discussed in light of the adaptation of the students to the learning network made up by two…

Developing 21st century skills through the use of student personal learning networks

Science.gov (United States)

Miller, Robert D.

This research was conducted to study the development of 21st century communication, collaboration, and digital literacy skills of students at the high school level through the use of online social network tools. The importance of this study was based on evidence high school and college students are not graduating with the requisite skills of communication, collaboration, and digital literacy skills yet employers see these skills important to the success of their employees. The challenge addressed through this study was how high schools can integrate social network tools into traditional learning environments to foster the development of these 21st century skills. A qualitative research study was completed through the use of case study. One high school class in a suburban high performing town in Connecticut was selected as the research site and the sample population of eleven student participants engaged in two sets of interviews and learned through the use social network tools for one semester of the school year. The primary social network tools used were Facebook, Diigo, Google Sites, Google Docs, and Twitter. The data collected and analyzed partially supported the transfer of the theory of connectivism at the high school level. The students actively engaged in collaborative learning and research. Key results indicated a heightened engagement in learning, the development of collaborative learning and research skills, and a greater understanding of how to use social network tools for effective public communication. The use of social network tools with high school students was a positive experience that led to an increased awareness of the students as to the benefits social network tools have as a learning tool. The data supported the continued use of social network tools to develop 21st century communication, collaboration, and digital literacy skills. Future research in this area may explore emerging social network tools as well as the long term impact these tools

Patchworking Network Structures

DEFF Research Database (Denmark)

Norus, Jesper

2004-01-01

analyzes fourdifferent managerial strategies of how to create network structures to deal with theinterfaces between industry, university and public institutions. The research-orientedstrategy, the incubator strategy, the industrial-partnering strategy, and the policyorientedstrategy. The research...... groups has been treated as a contingent factor.However, little attention has been given to the managerial efforts that entrepreneurshave make to establish the fit between small firms, university research, and publicpolicies such as regulatory policies and R&D policies through network-type structures.......New biotechnology organizations are perfect objects to study these relationshipsbecause new biotechnologies and techniques predominantly come from the universitysector (Kenney, 1986; Yoxen; 1984; Zucker & Darby, 1997; Robbins-Roth, 2001).From the perspective of the small biotechnology firms (SBFs,) this paper...

Networking for Learning The role of Networking in a Lifelong Learner's Professional Development

OpenAIRE

Rajagopal, Kamakshi

2016-01-01

This dissertation discusses the role the social activity of networking plays in lifelong learners’ professional and personal continuous development. The main hypothesis of this thesis is that networking is a learning strategy for lifelong learners, in which conversations are key activities through which they reassess their held thoughts and make sense of their experiences together with others.

Single-hidden-layer feed-forward quantum neural network based on Grover learning.

Science.gov (United States)

Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min

2013-09-01

In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning. Copyright © 2013 Elsevier Ltd. All rights reserved.

Optimizing the De-Noise Neural Network Model for GPS Time-Series Monitoring of Structures

Directory of Open Access Journals (Sweden)

Mosbeh R. Kaloop

2015-09-01

Full Text Available The Global Positioning System (GPS is recently used widely in structures and other applications. Notwithstanding, the GPS accuracy still suffers from the errors afflicting the measurements, particularly the short-period displacement of structural components. Previously, the multi filter method is utilized to remove the displacement errors. This paper aims at using a novel application for the neural network prediction models to improve the GPS monitoring time series data. Four prediction models for the learning algorithms are applied and used with neural network solutions: back-propagation, Cascade-forward back-propagation, adaptive filter and extended Kalman filter, to estimate which model can be recommended. The noise simulation and bridge’s short-period GPS of the monitoring displacement component of one Hz sampling frequency are used to validate the four models and the previous method. The results show that the Adaptive neural networks filter is suggested for de-noising the observations, specifically for the GPS displacement components of structures. Also, this model is expected to have significant influence on the design of structures in the low frequency responses and measurements’ contents.

Enhancing Formal E-Learning with Edutainment on Social Networks

Science.gov (United States)

Labus, A.; Despotovic-Zrakic, M.; Radenkovic, B.; Bogdanovic, Z.; Radenkovic, M.

2015-01-01

This paper reports on the investigation of the possibilities of enhancing the formal e-learning process by harnessing the potential of informal game-based learning on social networks. The goal of the research is to improve the outcomes of the formal learning process through the design and implementation of an educational game on a social network…

Learn-and-Adapt Stochastic Dual Gradients for Network Resource Allocation

OpenAIRE

Chen, Tianyi; Ling, Qing; Giannakis, Georgios B.

2017-01-01

Network resource allocation shows revived popularity in the era of data deluge and information explosion. Existing stochastic optimization approaches fall short in attaining a desirable cost-delay tradeoff. Recognizing the central role of Lagrange multipliers in network resource allocation, a novel learn-and-adapt stochastic dual gradient (LA-SDG) method is developed in this paper to learn the sample-optimal Lagrange multiplier from historical data, and accordingly adapt the upcoming resource...

Network structure and travel time perception.

Science.gov (United States)

Parthasarathi, Pavithra; Levinson, David; Hochmair, Hartwig

2013-01-01

The purpose of this research is to test the systematic variation in the perception of travel time among travelers and relate the variation to the underlying street network structure. Travel survey data from the Twin Cities metropolitan area (which includes the cities of Minneapolis and St. Paul) is used for the analysis. Travelers are classified into two groups based on the ratio of perceived and estimated commute travel time. The measures of network structure are estimated using the street network along the identified commute route. T-test comparisons are conducted to identify statistically significant differences in estimated network measures between the two traveler groups. The combined effect of these estimated network measures on travel time is then analyzed using regression models. The results from the t-test and regression analyses confirm the influence of the underlying network structure on the perception of travel time.

Information transfer in community structured multiplex networks

Science.gov (United States)

Solé Ribalta, Albert; Granell, Clara; Gómez, Sergio; Arenas, Alex

2015-08-01

The study of complex networks that account for different types of interactions has become a subject of interest in the last few years, specially because its representational power in the description of users interactions in diverse online social platforms (Facebook, Twitter, Instagram, etc.). The mathematical description of these interacting networks has been coined under the name of multilayer networks, where each layer accounts for a type of interaction. It has been shown that diffusive processes on top of these networks present a phenomenology that cannot be explained by the naive superposition of single layer diffusive phenomena but require the whole structure of interconnected layers. Nevertheless, the description of diffusive phenomena on multilayer networks has obviated the fact that social networks have strong mesoscopic structure represented by different communities of individuals driven by common interests, or any other social aspect. In this work, we study the transfer of information in multilayer networks with community structure. The final goal is to understand and quantify, if the existence of well-defined community structure at the level of individual layers, together with the multilayer structure of the whole network, enhances or deteriorates the diffusion of packets of information.

Information transfer in community structured multiplex networks

Directory of Open Access Journals (Sweden)

Albert eSolé Ribalta

2015-08-01

Full Text Available The study of complex networks that account for different types of interactions has become a subject of interest in the last few years, specially because its representational power in the description of users interactions in diverse online social platforms (Facebook, Twitter, Instagram, etc.. The mathematical description of these interacting networks has been coined under the name of multilayer networks, where each layer accounts for a type of interaction. It has been shown that diffusive processes on top of these networks present a phenomenology that cannot be explained by the naive superposition of single layer diffusive phenomena but require the whole structure of interconnected layers. Nevertheless, the description of diffusive phenomena on multilayer networks has obviated the fact that social networks have strong mesoscopic structure represented by different communities of individuals driven by common interests, or any other social aspect. In this work, we study the transfer of information in multilayer networks with community structure. The final goal is to understand and quantify, if the existence of well-defined community structure at the level of individual layers, together with the multilayer structure of the whole network, enhances or deteriorates the diffusion of packets of information.

Advanced Polymer Network Structures

Science.gov (United States)

2016-02-01

attractive interaction (n = 2.0) and a neutral interaction (n = 1.0); n is equal to unity for self-interactions among the monomers of first network and...... Network Structures by Robert Lambeth, Joseph Lenhart, and Tim Sirk Weapons and Materials Research Directorate, ARL Yelena Sliozberg TKC Global

Epidemic spreading on complex networks with community structures

NARCIS (Netherlands)

Stegehuis, C.; van der Hofstad, R.W.; van Leeuwaarden, J.S.H.

2016-01-01

Many real-world networks display a community structure. We study two random graph models that create a network with similar community structure as a given network. One model preserves the exact community structure of the original network, while the other model only preserves the set of communities

Biomimetic Hybrid Feedback Feedforward Neural-Network Learning Control.

Science.gov (United States)

Pan, Yongping; Yu, Haoyong

2017-06-01

This brief presents a biomimetic hybrid feedback feedforward neural-network learning control (NNLC) strategy inspired by the human motor learning control mechanism for a class of uncertain nonlinear systems. The control structure includes a proportional-derivative controller acting as a feedback servo machine and a radial-basis-function (RBF) NN acting as a feedforward predictive machine. Under the sufficient constraints on control parameters, the closed-loop system achieves semiglobal practical exponential stability, such that an accurate NN approximation is guaranteed in a local region along recurrent reference trajectories. Compared with the existing NNLC methods, the novelties of the proposed method include: 1) the implementation of an adaptive NN control to guarantee plant states being recurrent is not needed, since recurrent reference signals rather than plant states are utilized as NN inputs, which greatly simplifies the analysis and synthesis of the NNLC and 2) the domain of NN approximation can be determined a priori by the given reference signals, which leads to an easy construction of the RBF-NNs. Simulation results have verified the effectiveness of this approach.

Students' Feedback of mDPBL Approach and the Learning Impact towards Computer Networks Teaching and Learning

Science.gov (United States)

Winarno, Sri; Muthu, Kalaiarasi Sonai; Ling, Lew Sook

2018-01-01

This study presents students' feedback and learning impact on design and development of a multimedia learning in Direct Problem-Based Learning approach (mDPBL) for Computer Networks in Dian Nuswantoro University, Indonesia. This study examined the usefulness, contents and navigation of the multimedia learning as well as learning impacts towards…

Unsupervised learning in neural networks with short range synapses

Science.gov (United States)

Brunnet, L. G.; Agnes, E. J.; Mizusaki, B. E. P.; Erichsen, R., Jr.

2013-01-01

Different areas of the brain are involved in specific aspects of the information being processed both in learning and in memory formation. For example, the hippocampus is important in the consolidation of information from short-term memory to long-term memory, while emotional memory seems to be dealt by the amygdala. On the microscopic scale the underlying structures in these areas differ in the kind of neurons involved, in their connectivity, or in their clustering degree but, at this level, learning and memory are attributed to neuronal synapses mediated by longterm potentiation and long-term depression. In this work we explore the properties of a short range synaptic connection network, a nearest neighbor lattice composed mostly by excitatory neurons and a fraction of inhibitory ones. The mechanism of synaptic modification responsible for the emergence of memory is Spike-Timing-Dependent Plasticity (STDP), a Hebbian-like rule, where potentiation/depression is acquired when causal/non-causal spikes happen in a synapse involving two neurons. The system is intended to store and recognize memories associated to spatial external inputs presented as simple geometrical forms. The synaptic modifications are continuously applied to excitatory connections, including a homeostasis rule and STDP. In this work we explore the different scenarios under which a network with short range connections can accomplish the task of storing and recognizing simple connected patterns.

Networked learning in, for, and with the world

DEFF Research Database (Denmark)

Nørgård, Rikke Toft; Mor, Yishay; Bengtsen, Søren Smedegaard

2018-01-01

With the so-called ‘Mode 3’ university as overarching framework (Barnett, 2004; Bengtsen & Nørgård, 2016; Barnett & Bengtsen, 2017; Nørgård, Olesen & Toft-Nielsen, 2018) this chapter considers how traditional forms of and formats for teaching and learning within higher education can be rethought,......’ in higher education. In the following sections, we will describe these transformations of university being, before considering some of the new challenges, opportunities, and potentials of teaching and learning in and through hybrid networks in the Mode 3 institution......., opportunities, and potentials to the teaching and learning that takes place at the university. Through history, and across different present national contexts and cultures, the ‘being’ of the university and its livelihood and mandate has changed (Wright, 2016; Barnett, 2018). Through these transformations where......, reconfigured, and redesigned in order to facilitate valuable, meaningful and relevant hybrid networked learning in, for, and with the world. What it means to ‘be’ a university is changing and the university is a ‘being’ that in itself is changing (Barnett, 2011), something also offering challenges...

RELATION BETWEEN COOPERATION AND ORGANIZATIONAL LEARNING WITH THE COMPETITIVENESS IN AN INTERORGANIZATIONAL NETWORK

Directory of Open Access Journals (Sweden)

Paulo Cesar Zonta

2015-05-01

Full Text Available The study analyzed the relationship between cooperation and organizational learning with competitiveness in a small and medium enterprises (SME network, with business of the groups of the Commercial and Industrial Association of Chapecó (ACIC. The methodology used was quantitative, with the factorial analysis. Currently, ACIC has 14 groups and 236 SME´s nucleated, developing joint activities of economic and social sustainability in Chapecó. The theoretical study raised concepts already endorsed by the scientific community on interorganizational networks, competitiveness, cooperation and organizational learning. The results demonstrated that indicators related to cooperation and learning in horizontal networks are characterized as antecedents of competitiveness in organizational networks, and that there is a positive correlation between the constructs cooperation and organizational learning with competitiveness construct. The study confirms the belief that small businesses associated in networks can increase their competitiveness, thus contributing to regional development.

Global Electricity Trade Network: Structures and Implications

Science.gov (United States)

Ji, Ling; Jia, Xiaoping; Chiu, Anthony S. F.; Xu, Ming

2016-01-01

Nations increasingly trade electricity, and understanding the structure of the global power grid can help identify nations that are critical for its reliability. This study examines the global grid as a network with nations as nodes and international electricity trade as links. We analyze the structure of the global electricity trade network and find that the network consists of four sub-networks, and provide a detailed analysis of the largest network, Eurasia. Russia, China, Ukraine, and Azerbaijan have high betweenness measures in the Eurasian sub-network, indicating the degrees of centrality of the positions they hold. The analysis reveals that the Eurasian sub-network consists of seven communities based on the network structure. We find that the communities do not fully align with geographical proximity, and that the present international electricity trade in the Eurasian sub-network causes an approximately 11 million additional tons of CO2 emissions. PMID:27504825

Social Networking as a Facilitator for Lifelong Learning in Multinational Employee’s Career

Directory of Open Access Journals (Sweden)

Andreea Nicoleta VISAN

2017-01-01

Full Text Available This paper discusses how multinational employees who are leaving in Bucharest, Romania use social networks as a tool for their everyday tasks and work, and how they want to satisfy their personal development needs by having access to information from these digital platforms. The case study described was conducted in Bucharest in 2017 and followed a results analysis with structured tables and graphs. In the study took part 24 participants who were selected among multinational IT employees in Bucharest. Social networks contribute to employee’s lifelong educational process: besides providing them positive gratification, they also contribute to their personal development and careers growth. Even though all individuals who participated in this study use social networks, more efforts should be done in order for companies in Bucharest to know the benefits of social networks and employee’s opinion about their contribution to lifelong learning.

Structure Mapping for Social Learning.

Science.gov (United States)

Christie, Stella

2017-07-01

Analogical reasoning is a foundational tool for human learning, allowing learners to recognize relational structures in new events and domains. Here I sketch some grounds for understanding and applying analogical reasoning in social learning. The social world is fundamentally characterized by relations between people, with common relational structures-such as kinships and social hierarchies-forming social units that dictate social behaviors. Just as young learners use analogical reasoning for learning relational structures in other domains-spatial relations, verbs, relational categories-analogical reasoning ought to be a useful cognitive tool for acquiring social relations and structures. Copyright © 2017 Cognitive Science Society, Inc.

Language Views on Social Networking Sites for Language Learning: The Case of Busuu

Science.gov (United States)

Álvarez Valencia, José Aldemar

2016-01-01

Social networking has compelled the area of computer-assisted language learning (CALL) to expand its research palette and account for new virtual ecologies that afford language learning and socialization. This study focuses on Busuu, a social networking site for language learning (SNSLL), and analyzes the views of language that are enacted through…

Social Networks: Rational Learning and Information Aggregation

Science.gov (United States)

2009-09-01

predecessor, Gale and Kariv (2003) who generalize the payoff equalization result of Bala and Goyal (1998) in connected social networks (discussed below...requires more notation. Using Bayes’ Rule and the assumption of equal priors on the state θ, we have that the social belief given by observing... Social Networks: Rational Learning and Information Aggregation by Ilan Lobel B.Sc., Pontif́ıcia Universidade Católica do Rio de Janeiro (2004

Learning Transferable Features with Deep Adaptation Networks

OpenAIRE

Long, Mingsheng; Cao, Yue; Wang, Jianmin; Jordan, Michael I.

2015-01-01

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation...

Stochastic Online Learning in Dynamic Networks under Unknown Models

Science.gov (United States)

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

Multi-threshold white matter structural networks fusion for accurate diagnosis of Tourette syndrome children

Science.gov (United States)

Wen, Hongwei; Liu, Yue; Wang, Shengpei; Li, Zuoyong; Zhang, Jishui; Peng, Yun; He, Huiguang

2017-03-01

Tourette syndrome (TS) is a childhood-onset neurobehavioral disorder. To date, TS is still misdiagnosed due to its varied presentation and lacking of obvious clinical symptoms. Therefore, studies of objective imaging biomarkers are of great importance for early TS diagnosis. As tic generation has been linked to disturbed structural networks, and many efforts have been made recently to investigate brain functional or structural networks using machine learning methods, for the purpose of disease diagnosis. However, few studies were related to TS and some drawbacks still existed in them. Therefore, we propose a novel classification framework integrating a multi-threshold strategy and a network fusion scheme to address the preexisting drawbacks. Here we used diffusion MRI probabilistic tractography to construct the structural networks of 44 TS children and 48 healthy children. We ameliorated the similarity network fusion algorithm specially to fuse the multi-threshold structural networks. Graph theoretical analysis was then implemented, and nodal degree, nodal efficiency and nodal betweenness centrality were selected as features. Finally, support vector machine recursive feature extraction (SVM-RFE) algorithm was used for feature selection, and then optimal features are fed into SVM to automatically discriminate TS children from controls. We achieved a high accuracy of 89.13% evaluated by a nested cross validation, demonstrated the superior performance of our framework over other comparison methods. The involved discriminative regions for classification primarily located in the basal ganglia and frontal cortico-cortical networks, all highly related to the pathology of TS. Together, our study may provide potential neuroimaging biomarkers for early-stage TS diagnosis.

Perspectives on Advanced Learning Technologies and Learning Networks and Future Aerospace Workforce Environments

Science.gov (United States)

Noor, Ahmed K. (Compiler)

2003-01-01

An overview of the advanced learning technologies is given in this presentation along with a brief description of their impact on future aerospace workforce development. The presentation is divided into five parts (see Figure 1). In the first part, a brief historical account of the evolution of learning technologies is given. The second part describes the current learning activities. The third part describes some of the future aerospace systems, as examples of high-tech engineering systems, and lists their enabling technologies. The fourth part focuses on future aerospace research, learning and design environments. The fifth part lists the objectives of the workshop and some of the sources of information on learning technologies and learning networks.

Language Learning through Social Networks: Perceptions and Reality

Science.gov (United States)

Lin, Chin-Hsi; Warschauer, Mark; Blake, Robert

2016-01-01

Language Learning Social Network Sites (LLSNSs) have attracted millions of users around the world. However, little is known about how people participate in these sites and what they learn from them. This study investigated learners' attitudes, usage, and progress in a major LLSNS through a survey of 4,174 as well as 20 individual case studies. The…

Understanding the Context of Learning in an Online Social Network for Health Professionals' Informal Learning.

Science.gov (United States)

Li, Xin; Gray, Kathleen; Verspoor, Karin; Barnett, Stephen

2017-01-01

Online social networks (OSN) enable health professionals to learn informally, for example by sharing medical knowledge, or discussing practice management challenges and clinical issues. Understanding the learning context in OSN is necessary to get a complete picture of the learning process, in order to better support this type of learning. This study proposes critical contextual factors for understanding the learning context in OSN for health professionals, and demonstrates how these contextual factors can be used to analyse the learning context in a designated online learning environment for health professionals.

Continuous Learning of a Multilayered Network Topology in a Video Camera Network

Directory of Open Access Journals (Sweden)

Zou Xiaotao

2009-01-01

Full Text Available Abstract A multilayered camera network architecture with nodes as entry/exit points, cameras, and clusters of cameras at different layers is proposed. Unlike existing methods that used discrete events or appearance information to infer the network topology at a single level, this paper integrates face recognition that provides robustness to appearance changes and better models the time-varying traffic patterns in the network. The statistical dependence between the nodes, indicating the connectivity and traffic patterns of the camera network, is represented by a weighted directed graph and transition times that may have multimodal distributions. The traffic patterns and the network topology may be changing in the dynamic environment. We propose a Monte Carlo Expectation-Maximization algorithm-based continuous learning mechanism to capture the latent dynamically changing characteristics of the network topology. In the experiments, a nine-camera network with twenty-five nodes (at the lowest level is analyzed both in simulation and in real-life experiments and compared with previous approaches.

Continuous Learning of a Multilayered Network Topology in a Video Camera Network

Directory of Open Access Journals (Sweden)

Xiaotao Zou

2009-01-01

Full Text Available A multilayered camera network architecture with nodes as entry/exit points, cameras, and clusters of cameras at different layers is proposed. Unlike existing methods that used discrete events or appearance information to infer the network topology at a single level, this paper integrates face recognition that provides robustness to appearance changes and better models the time-varying traffic patterns in the network. The statistical dependence between the nodes, indicating the connectivity and traffic patterns of the camera network, is represented by a weighted directed graph and transition times that may have multimodal distributions. The traffic patterns and the network topology may be changing in the dynamic environment. We propose a Monte Carlo Expectation-Maximization algorithm-based continuous learning mechanism to capture the latent dynamically changing characteristics of the network topology. In the experiments, a nine-camera network with twenty-five nodes (at the lowest level is analyzed both in simulation and in real-life experiments and compared with previous approaches.

Analog memristive synapse in spiking networks implementing unsupervised learning

Directory of Open Access Journals (Sweden)

Erika Covi

2016-10-01

Full Text Available Emerging brain-inspired architectures call for devices that can emulate the functionality of biological synapses in order to implement new efficient computational schemes able to solve ill-posed problems. Various devices and solutions are still under investigation and, in this respect, a challenge is opened to the researchers in the field. Indeed, the optimal candidate is a device able to reproduce the complete functionality of a synapse, i.e. the typical synaptic process underlying learning in biological systems (activity-dependent synaptic plasticity. This implies a device able to change its resistance (synaptic strength, or weight upon proper electrical stimuli (synaptic activity and showing several stable resistive states throughout its dynamic range (analog behavior. Moreover, it should be able to perform spike timing dependent plasticity (STDP, an associative homosynaptic plasticity learning rule based on the delay time between the two firing neurons the synapse is connected to. This rule is a fundamental learning protocol in state-of-art networks, because it allows unsupervised learning. Notwithstanding this fact, STDP-based unsupervised learning has been proposed several times mainly for binary synapses rather than multilevel synapses composed of many binary memristors. This paper proposes an HfO2-based analog memristor as a synaptic element which performs STDP within a small spiking neuromorphic network operating unsupervised learning for character recognition. The trained network is able to recognize five characters even in case incomplete or noisy characters are displayed and it is robust to a device-to-device variability of up to +/-30%.

Analog Memristive Synapse in Spiking Networks Implementing Unsupervised Learning.

Science.gov (United States)

Covi, Erika; Brivio, Stefano; Serb, Alexander; Prodromakis, Themis; Fanciulli, Marco; Spiga, Sabina

2016-01-01

Emerging brain-inspired architectures call for devices that can emulate the functionality of biological synapses in order to implement new efficient computational schemes able to solve ill-posed problems. Various devices and solutions are still under investigation and, in this respect, a challenge is opened to the researchers in the field. Indeed, the optimal candidate is a device able to reproduce the complete functionality of a synapse, i.e., the typical synaptic process underlying learning in biological systems (activity-dependent synaptic plasticity). This implies a device able to change its resistance (synaptic strength, or weight) upon proper electrical stimuli (synaptic activity) and showing several stable resistive states throughout its dynamic range (analog behavior). Moreover, it should be able to perform spike timing dependent plasticity (STDP), an associative homosynaptic plasticity learning rule based on the delay time between the two firing neurons the synapse is connected to. This rule is a fundamental learning protocol in state-of-art networks, because it allows unsupervised learning. Notwithstanding this fact, STDP-based unsupervised learning has been proposed several times mainly for binary synapses rather than multilevel synapses composed of many binary memristors. This paper proposes an HfO 2 -based analog memristor as a synaptic element which performs STDP within a small spiking neuromorphic network operating unsupervised learning for character recognition. The trained network is able to recognize five characters even in case incomplete or noisy images are displayed and it is robust to a device-to-device variability of up to ±30%.

Optimizing Knowledge Sharing In Learning Networks Through Peer Tutoring

NARCIS (Netherlands)

Hsiao, Amy; Brouns, Francis; Kester, Liesbeth; Sloep, Peter

2009-01-01

Hsiao, Y. P., Brouns, F., Kester, L., & Sloep, P. B. (2009). Optimizing Knowledge Sharing In Learning Networks Through Peer Tutoring. In D. Kinshuk, J. Sampson, J. Spector, P. Isaías, P. Barbosa & D. Ifenthaler (Eds.). Proceedings of IADIS International Conference Cognition and Exploratory Learning

Informal Learning and Identity Formation in Online Social Networks

Science.gov (United States)

Greenhow, Christine; Robelia, Beth

2009-01-01

All students today are increasingly expected to develop technological fluency, digital citizenship, and other twenty-first century competencies despite wide variability in the quality of learning opportunities schools provide. Social network sites (SNSs) available via the internet may provide promising contexts for learning to supplement…

Integrative gene network construction to analyze cancer recurrence using semi-supervised learning.

Science.gov (United States)

Park, Chihyun; Ahn, Jaegyoon; Kim, Hyunjin; Park, Sanghyun

2014-01-01

The prognosis of cancer recurrence is an important research area in bioinformatics and is challenging due to the small sample sizes compared to the vast number of genes. There have been several attempts to predict cancer recurrence. Most studies employed a supervised approach, which uses only a few labeled samples. Semi-supervised learning can be a great alternative to solve this problem. There have been few attempts based on manifold assumptions to reveal the detailed roles of identified cancer genes in recurrence. In order to predict cancer recurrence, we proposed a novel semi-supervised learning algorithm based on a graph regularization approach. We transformed the gene expression data into a graph structure for semi-supervised learning and integrated protein interaction data with the gene expression data to select functionally-related gene pairs. Then, we predicted the recurrence of cancer by applying a regularization approach to the constructed graph containing both labeled and unlabeled nodes. The average improvement rate of accuracy for three different cancer datasets was 24.9% compared to existing supervised and semi-supervised methods. We performed functional enrichment on the gene networks used for learning. We identified that those gene networks are significantly associated with cancer-recurrence-related biological functions. Our algorithm was developed with standard C++ and is available in Linux and MS Windows formats in the STL library. The executable program is freely available at: http://embio.yonsei.ac.kr/~Park/ssl.php.

Integrative gene network construction to analyze cancer recurrence using semi-supervised learning.

Directory of Open Access Journals (Sweden)

Chihyun Park

Full Text Available BACKGROUND: The prognosis of cancer recurrence is an important research area in bioinformatics and is challenging due to the small sample sizes compared to the vast number of genes. There have been several attempts to predict cancer recurrence. Most studies employed a supervised approach, which uses only a few labeled samples. Semi-supervised learning can be a great alternative to solve this problem. There have been few attempts based on manifold assumptions to reveal the detailed roles of identified cancer genes in recurrence. RESULTS: In order to predict cancer recurrence, we proposed a novel semi-supervised learning algorithm based on a graph regularization approach. We transformed the gene expression data into a graph structure for semi-supervised learning and integrated protein interaction data with the gene expression data to select functionally-related gene pairs. Then, we predicted the recurrence of cancer by applying a regularization approach to the constructed graph containing both labeled and unlabeled nodes. CONCLUSIONS: The average improvement rate of accuracy for three different cancer datasets was 24.9% compared to existing supervised and semi-supervised methods. We performed functional enrichment on the gene networks used for learning. We identified that those gene networks are significantly associated with cancer-recurrence-related biological functions. Our algorithm was developed with standard C++ and is available in Linux and MS Windows formats in the STL library. The executable program is freely available at: http://embio.yonsei.ac.kr/~Park/ssl.php.

Active vision and image/video understanding with decision structures based on the network-symbolic models

Science.gov (United States)

Kuvich, Gary

2003-08-01

Vision is a part of a larger information system that converts visual information into knowledge structures. These structures drive vision process, resolve ambiguity and uncertainty via feedback projections, and provide image understanding that is an interpretation of visual information in terms of such knowledge models. The ability of human brain to emulate knowledge structures in the form of networks-symbolic models is found. And that means an important shift of paradigm in our knowledge about brain from neural networks to "cortical software". Symbols, predicates and grammars naturally emerge in such active multilevel hierarchical networks, and logic is simply a way of restructuring such models. Brain analyzes an image as a graph-type decision structure created via multilevel hierarchical compression of visual information. Mid-level vision processes like clustering, perceptual grouping, separation of figure from ground, are special kinds of graph/network transformations. They convert low-level image structure into the set of more abstract ones, which represent objects and visual scene, making them easy for analysis by higher-level knowledge structures. Higher-level vision phenomena are results of such analysis. Composition of network-symbolic models works similar to frames and agents, combines learning, classification, analogy together with higher-level model-based reasoning into a single framework. Such models do not require supercomputers. Based on such principles, and using methods of Computational intelligence, an Image Understanding system can convert images into the network-symbolic knowledge models, and effectively resolve uncertainty and ambiguity, providing unifying representation for perception and cognition. That allows creating new intelligent computer vision systems for robotic and defense industries.

Gene Network Construction from Microarray Data Identifies a Key Network Module and Several Candidate Hub Genes in Age-Associated Spatial Learning Impairment.

Science.gov (United States)

Uddin, Raihan; Singh, Shiva M

2017-01-01

As humans age many suffer from a decrease in normal brain functions including spatial learning impairments. This study aimed to better understand the molecular mechanisms in age-associated spatial learning impairment (ASLI). We used a mathematical modeling approach implemented in Weighted Gene Co-expression Network Analysis (WGCNA) to create and compare gene network models of young (learning unimpaired) and aged (predominantly learning impaired) brains from a set of exploratory datasets in rats in the context of ASLI. The major goal was to overcome some of the limitations previously observed in the traditional meta- and pathway analysis using these data, and identify novel ASLI related genes and their networks based on co-expression relationship of genes. This analysis identified a set of network modules in the young, each of which is highly enriched with genes functioning in broad but distinct GO functional categories or biological pathways. Interestingly, the analysis pointed to a single module that was highly enriched with genes functioning in "learning and memory" related functions and pathways. Subsequent differential network analysis of this "learning and memory" module in the aged (predominantly learning impaired) rats compared to the young learning unimpaired rats allowed us to identify a set of novel ASLI candidate hub genes. Some of these genes show significant repeatability in networks generated from independent young and aged validation datasets. These hub genes are highly co-expressed with other genes in the network, which not only show differential expression but also differential co-expression and differential connectivity across age and learning impairment. The known function of these hub genes indicate that they play key roles in critical pathways, including kinase and phosphatase signaling, in functions related to various ion channels, and in maintaining neuronal integrity relating to synaptic plasticity and memory formation. Taken together, they

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.

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks.

Science.gov (United States)

Carpenter, Gail A.

1997-11-01

A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dART reduces to fuzzy ART and the supervised model dARTMAP reduces to fuzzy ARTMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. Distributed ART models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold. Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match-reset-search process also helps stabilize memory. Without the match-reset-search system, dART becomes a type of distributed competitive learning network.

Network Ecology and Adolescent Social Structure.

Science.gov (United States)

McFarland, Daniel A; Moody, James; Diehl, David; Smith, Jeffrey A; Thomas, Reuben J

2014-12-01

Adolescent societies-whether arising from weak, short-term classroom friendships or from close, long-term friendships-exhibit various levels of network clustering, segregation, and hierarchy. Some are rank-ordered caste systems and others are flat, cliquish worlds. Explaining the source of such structural variation remains a challenge, however, because global network features are generally treated as the agglomeration of micro-level tie-formation mechanisms, namely balance, homophily, and dominance. How do the same micro-mechanisms generate significant variation in global network structures? To answer this question we propose and test a network ecological theory that specifies the ways features of organizational environments moderate the expression of tie-formation processes, thereby generating variability in global network structures across settings. We develop this argument using longitudinal friendship data on schools (Add Health study) and classrooms (Classroom Engagement study), and by extending exponential random graph models to the study of multiple societies over time.

Machine Learning for ATLAS DDM Network Metrics

CERN Document Server

Lassnig, Mario; The ATLAS collaboration; Vamosi, Ralf

2016-01-01

The increasing volume of physics data is posing a critical challenge to the ATLAS experiment. In anticipation of high luminosity physics, automation of everyday data management tasks has become necessary. Previously many of these tasks required human decision-making and operation. Recent advances in hardware and software have made it possible to entrust more complicated duties to automated systems using models trained by machine learning algorithms. In this contribution we show results from our ongoing automation efforts. First, we describe our framework for distributed data management and network metrics, automatically extract and aggregate data, train models with various machine learning algorithms, and eventually score the resulting models and parameters. Second, we use these models to forecast metrics relevant for network-aware job scheduling and data brokering. We show the characteristics of the data and evaluate the forecasting accuracy of our models.

Do technologies have politics? The new paradigm and pedagogy in networked learning

OpenAIRE

Jones, Chris

2001-01-01

This paper explores the relationships between the technologies deployed in networked and e-Learning and the pedagogies and politics associated with them. Networked learning and the related move to e-Learning are coincident with the globalisation, commodification and massification of Higher Education. It examines the hard and soft forms of technological determinism (TD) found in the current advocacy of technological futures for Higher Education. Hard TD claims that new technologies bring about...

Communication on the structure of biological networks

Indian Academy of Sciences (India)

Networks are widely used to represent interaction pattern among the components in complex systems. Structures of real networks from different domains may vary quite significantly. As there is an interplay between network architecture and dynamics, structure plays an important role in communication and spreading of ...

Enhancing Teaching and Learning Wi-Fi Networking Using Limited Resources to Undergraduates

Science.gov (United States)

Sarkar, Nurul I.

2013-01-01

Motivating students to learn Wi-Fi (wireless fidelity) wireless networking to undergraduate students is often difficult because many students find the subject rather technical and abstract when presented in traditional lecture format. This paper focuses on the teaching and learning aspects of Wi-Fi networking using limited hardware resources. It…

Saliency U-Net: A regional saliency map-driven hybrid deep learning network for anomaly segmentation

Science.gov (United States)

Karargyros, Alex; Syeda-Mahmood, Tanveer

2018-02-01

Deep learning networks are gaining popularity in many medical image analysis tasks due to their generalized ability to automatically extract relevant features from raw images. However, this can make the learning problem unnecessarily harder requiring network architectures of high complexity. In case of anomaly detection, in particular, there is often sufficient regional difference between the anomaly and the surrounding parenchyma that could be easily highlighted through bottom-up saliency operators. In this paper we propose a new hybrid deep learning network using a combination of raw image and such regional maps to more accurately learn the anomalies using simpler network architectures. Specifically, we modify a deep learning network called U-Net using both the raw and pre-segmented images as input to produce joint encoding (contraction) and expansion paths (decoding) in the U-Net. We present results of successfully delineating subdural and epidural hematomas in brain CT imaging and liver hemangioma in abdominal CT images using such network.

The Livermore Brain: Massive Deep Learning Networks Enabled by High Performance Computing

Energy Technology Data Exchange (ETDEWEB)

Chen, Barry Y. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

2016-11-29

The proliferation of inexpensive sensor technologies like the ubiquitous digital image sensors has resulted in the collection and sharing of vast amounts of unsorted and unexploited raw data. Companies and governments who are able to collect and make sense of large datasets to help them make better decisions more rapidly will have a competitive advantage in the information era. Machine Learning technologies play a critical role for automating the data understanding process; however, to be maximally effective, useful intermediate representations of the data are required. These representations or “features” are transformations of the raw data into a form where patterns are more easily recognized. Recent breakthroughs in Deep Learning have made it possible to learn these features from large amounts of labeled data. The focus of this project is to develop and extend Deep Learning algorithms for learning features from vast amounts of unlabeled data and to develop the HPC neural network training platform to support the training of massive network models. This LDRD project succeeded in developing new unsupervised feature learning algorithms for images and video and created a scalable neural network training toolkit for HPC. Additionally, this LDRD helped create the world’s largest freely-available image and video dataset supporting open multimedia research and used this dataset for training our deep neural networks. This research helped LLNL capture several work-for-others (WFO) projects, attract new talent, and establish collaborations with leading academic and commercial partners. Finally, this project demonstrated the successful training of the largest unsupervised image neural network using HPC resources and helped establish LLNL leadership at the intersection of Machine Learning and HPC research.