Sample records for bayesian neural network

  1. Option Pricing Using Bayesian Neural Networks

    Pires, Michael Maio


    Options have provided a field of much study because of the complexity involved in pricing them. The Black-Scholes equations were developed to price options but they are only valid for European styled options. There is added complexity when trying to price American styled options and this is why the use of neural networks has been proposed. Neural Networks are able to predict outcomes based on past data. The inputs to the networks here are stock volatility, strike price and time to maturity with the output of the network being the call option price. There are two techniques for Bayesian neural networks used. One is Automatic Relevance Determination (for Gaussian Approximation) and one is a Hybrid Monte Carlo method, both used with Multi-Layer Perceptrons.

  2. Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks

    Hernández-Lobato, José Miguel; Adams, Ryan P.


    Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a large number of hyperparameters to the data, lack of calibrated probabilistic predictions, and a tendency to overfit the training data. In principle, the Bayesian approach to learning neural networks does not have these problems. However, existing Bayesian ...

  3. Recurrent Bayesian Reasoning in Probabilistic Neural Networks

    Grim, Jiří; Hora, Jan

    Vol. Part I. Berlin: Springer, 2007 - (Marques de Sá, J.; Alexandre, L.; Duch, W.; Mandic, D.), s. 129-138. (Lecture Notes in Computer Scinece. SL 1 - Theoretical Computer Science and General Issues. 4669). ISBN 3-540-74693-5. [International Conference on Artificial Neural Networks /17./. Porto (PT), 09.09.2007-13.09.2007] R&D Projects: GA MŠk 1M0572; GA ČR GA102/07/1594 EU Projects: European Commission(XE) 507752 - MUSCLE Grant ostatní: GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : neural networks * probabilistic approach * distribution mixtures Subject RIV: BD - Theory of Information

  4. Nuclear charge radii: Density functional theory meets Bayesian neural networks

    Utama, Raditya; Piekarewicz, Jorge


    The distribution of electric charge in atomic nuclei is fundamental to our understanding of the complex nuclear dynamics and a quintessential observable to validate nuclear structure models. We explore a novel approach that combines sophisticated models of nuclear structure with Bayesian neural networks (BNN) to generate predictions for the charge radii of thousands of nuclei throughout the nuclear chart. A class of relativistic energy density functionals is used to provide robust predictions for nuclear charge radii. In turn, these predictions are refined through Bayesian learning for a neural network that is trained using residuals between theoretical predictions and the experimental data. Although predictions obtained with density functional theory provide a fairly good description of experiment, our results show significant improvement (better than 40%) after BNN refinement. Moreover, these improved results for nuclear charge radii are supplemented with theoretical error bars. We have successfully demonst...

  5. Bayesian Methods for Neural Networks and Related Models

    Titterington, D.M.


    Models such as feed-forward neural networks and certain other structures investigated in the computer science literature are not amenable to closed-form Bayesian analysis. The paper reviews the various approaches taken to overcome this difficulty, involving the use of Gaussian approximations, Markov chain Monte Carlo simulation routines and a class of non-Gaussian but “deterministic” approximations called variational approximations.

  6. Markov Chain Monte Carlo Bayesian Learning for Neural Networks

    Goodrich, Michael S.


    Conventional training methods for neural networks involve starting al a random location in the solution space of the network weights, navigating an error hyper surface to reach a minimum, and sometime stochastic based techniques (e.g., genetic algorithms) to avoid entrapment in a local minimum. It is further typically necessary to preprocess the data (e.g., normalization) to keep the training algorithm on course. Conversely, Bayesian based learning is an epistemological approach concerned with formally updating the plausibility of competing candidate hypotheses thereby obtaining a posterior distribution for the network weights conditioned on the available data and a prior distribution. In this paper, we developed a powerful methodology for estimating the full residual uncertainty in network weights and therefore network predictions by using a modified Jeffery's prior combined with a Metropolis Markov Chain Monte Carlo method.

  7. Bayesian and neural networks for preliminary ship design

    Clausen, H. B.; Lützen, Marie; Friis-Hansen, Andreas; Bjørneboe, Nanna Katrine


    examples, the three methods are evaluated in terms of accuracy and limitations of use. For different types of ships, the methods provide information on the relations between length, breadth, height, draft, speed, displacement, block coefficient and loading capacity. Thus, useful tools are available to the...... 000 ships is acquired and various methods for derivation of empirical relations are employed. A regression analysis is carried out to fit functions to the data. Further, the data are used to learn Bayesian and neural networks to encode the relations between the characteristics. On the basis of...

  8. Applying Hierarchical Bayesian Neural Network in Failure Time Prediction

    Ling-Jing Kao


    Full Text Available With the rapid technology development and improvement, the product failure time prediction becomes an even harder task because only few failures in the product life tests are recorded. The classical statistical model relies on the asymptotic theory and cannot guarantee that the estimator has the finite sample property. To solve this problem, we apply the hierarchical Bayesian neural network (HBNN approach to predict the failure time and utilize the Gibbs sampler of Markov chain Monte Carlo (MCMC to estimate model parameters. In this proposed method, the hierarchical structure is specified to study the heterogeneity among products. Engineers can use the heterogeneity estimates to identify the causes of the quality differences and further enhance the product quality. In order to demonstrate the effectiveness of the proposed hierarchical Bayesian neural network model, the prediction performance of the proposed model is evaluated using multiple performance measurement criteria. Sensitivity analysis of the proposed model is also conducted using different number of hidden nodes and training sample sizes. The result shows that HBNN can provide not only the predictive distribution but also the heterogeneous parameter estimates for each path.

  9. A novel Bayesian learning method for information aggregation in modular neural networks

    Wang, Pan; Xu, Lida; Zhou, Shang-Ming; Fan, Zhun; Li, Youfeng; Feng, Shan


    Modular neural network is a popular neural network model which has many successful applications. In this paper, a sequential Bayesian learning (SBL) is proposed for modular neural networks aiming at efficiently aggregating the outputs of members of the ensemble. The experimental results on eight ...... benchmark problems have demonstrated that the proposed method can perform information aggregation efficiently in data modeling....

  10. Evidence for single top quark production using Bayesian neural networks

    Kau, Daekwang; /Florida State U.


    We present results of a search for single top quark production in p{bar p} collisions using a dataset of approximately 1 fb{sup -1} collected with the D0 detector. This analysis considers the muon+jets and electron+jets final states and makes use of Bayesian neural networks to separate the expected signals from backgrounds. The observed excess is associated with a p-value of 0.081%, assuming the background-only hypothesis, which corresponds to an excess over background of 3.2 standard deviations for a Gaussian density. The p-value computed using the SM signal cross section of 2.9 pb is 1.6%, corresponding to an expected significance of 2.2 standard deviations. Assuming the observed excess is due to single top production, we measure a single top quark production cross section of {sigma}(p{bar p} {yields} tb + X, tqb + X) = 4.4 {+-} 1.5 pb.

  11. Bayesian estimation inherent in a Mexican-hat-type neural network

    Takiyama, Ken


    Brain functions, such as perception, motor control and learning, and decision making, have been explained based on a Bayesian framework, i.e., to decrease the effects of noise inherent in the human nervous system or external environment, our brain integrates sensory and a priori information in a Bayesian optimal manner. However, it remains unclear how Bayesian computations are implemented in the brain. Herein, I address this issue by analyzing a Mexican-hat-type neural network, which was used as a model of the visual cortex, motor cortex, and prefrontal cortex. I analytically demonstrate that the dynamics of an order parameter in the model corresponds exactly to a variational inference of a linear Gaussian state-space model, a Bayesian estimation, when the strength of recurrent synaptic connectivity is appropriately stronger than that of an external stimulus, a plausible condition in the brain. This exact correspondence can reveal the relationship between the parameters in the Bayesian estimation and those in the neural network, providing insight for understanding brain functions.

  12. Identification of information tonality based on Bayesian approach and neural networks

    Lande, D. V.


    A model of the identification of information tonality, based on Bayesian approach and neural networks was described. In the context of this paper tonality means positive or negative tone of both the whole information and its parts which are related to particular concepts. The method, its application is presented in the paper, is based on statistic regularities connected with the presence of definite lexemes in the texts. A distinctive feature of the method is its simplicity and versatility. A...

  13. Bayesian Regularization in a Neural Network Model to Estimate Lines of Code Using Function Points

    K. K. Aggarwal


    Full Text Available It is a well known fact that at the beginning of any project, the software industry needs to know, how much will it cost to develop and what would be the time required ? . This paper examines the potential of using a neural network model for estimating the lines of code, once the functional requirements are known. Using the International Software Benchmarking Standards Group (ISBSG Repository Data (release 9 for the experiment, this paper examines the performance of back propagation feed forward neural network to estimate the Source Lines of Code. Multiple training algorithms are used in the experiments. Results demonstrate that the neural network models trained using Bayesian Regularization provide the best results and are suitable for this purpose.

  14. Bayesian neural networks for bivariate binary data: an application to prostate cancer study.

    Chakraborty, Sounak; Ghosh, Malay; Maiti, Tapabrata; Tewari, Ashutosh


    Prostate cancer is one of the most common cancers in American men. The cancer could either be locally confined, or it could spread outside the organ. When locally confined, there are several options for treating and curing this disease. Otherwise, surgery is the only option, and in extreme cases of outside spread, it could very easily recur within a short time even after surgery and subsequent radiation therapy. Hence, it is important to know, based on pre-surgery biopsy results how likely the cancer is organ-confined or not. The paper considers a hierarchical Bayesian neural network approach for posterior prediction probabilities of certain features indicative of non-organ confined prostate cancer. In particular, we find such probabilities for margin positivity (MP) and seminal vesicle (SV) positivity jointly. The available training set consists of bivariate binary outcomes indicating the presence or absence of the two. In addition, we have certain covariates such as prostate specific antigen (PSA), gleason score and the indicator for the cancer to be unilateral or bilateral (i.e. spread on one or both sides) in one data set and gene expression microarrays in another data set. We take a hierarchical Bayesian neural network approach to find the posterior prediction probabilities for a test and validation set, and compare these with the actual outcomes for the first data set. In case of the microarray data we use leave one out cross-validation to access the accuracy of our method. We also demonstrate the superiority of our method to the other competing methods through a simulation study. The Bayesian procedure is implemented by an application of the Markov chain Monte Carlo numerical integration technique. For the problem at hand, our Bayesian bivariate neural network procedure is shown to be superior to the classical neural network, Radford Neal's Bayesian neural network as well as bivariate logistic models to predict jointly the MP and SV in a patient in both the

  15. Forecasting Rainfall Time Series with stochastic output approximated by neural networks Bayesian approach

    Cristian Rodriguez Rivero


    Full Text Available The annual estimate of the availability of the amount of water for the agricultural sector has become a lifetime in places where rainfall is scarce, as is the case of northwestern Argentina. This work proposes to model and simulate monthly rainfall time series from one geographical location of Catamarca, Valle El Viejo Portezuelo. In this sense, the time series prediction is mathematical and computational modelling series provided by monthly cumulative rainfall, which has stochastic output approximated by neural networks Bayesian approach. We propose to use an algorithm based on artificial neural networks (ANNs using the Bayesian inference. The result of the prediction consists of 20% of the provided data consisting of 2000 to 2010. A new analysis for modelling, simulation and computational prediction of cumulative rainfall from one geographical location is well presented. They are used as data information, only the historical time series of daily flows measured in mmH2O. Preliminary results of the annual forecast in mmH2O with a prediction horizon of one year and a half are presented, 18 months, respectively. The methodology employs artificial neural network based tools, statistical analysis and computer to complete the missing information and knowledge of the qualitative and quantitative behavior. They also show some preliminary results with different prediction horizons of the proposed filter and its comparison with the performance Gaussian process filter used in the literature.

  16. Explicitly integrating parameter, input, and structure uncertainties into Bayesian Neural Networks for probabilistic hydrologic forecasting

    Zhang, Xuesong


    Estimating uncertainty of hydrologic forecasting is valuable to water resources and other relevant decision making processes. Recently, Bayesian Neural Networks (BNNs) have been proved powerful tools for quantifying uncertainty of streamflow forecasting. In this study, we propose a Markov Chain Monte Carlo (MCMC) framework (BNN-PIS) to incorporate the uncertainties associated with parameters, inputs, and structures into BNNs. This framework allows the structure of the neural networks to change by removing or adding connections between neurons and enables scaling of input data by using rainfall multipliers. The results show that the new BNNs outperform BNNs that only consider uncertainties associated with parameters and model structures. Critical evaluation of posterior distribution of neural network weights, number of effective connections, rainfall multipliers, and hyper-parameters shows that the assumptions held in our BNNs are not well supported. Further understanding of characteristics of and interactions among different uncertainty sources is expected to enhance the application of neural networks for uncertainty analysis of hydrologic forecasting. © 2011 Elsevier B.V.

  17. Identification of information tonality based on Bayesian approach and neural networks

    Lande, D V


    A model of the identification of information tonality, based on Bayesian approach and neural networks was described. In the context of this paper tonality means positive or negative tone of both the whole information and its parts which are related to particular concepts. The method, its application is presented in the paper, is based on statistic regularities connected with the presence of definite lexemes in the texts. A distinctive feature of the method is its simplicity and versatility. At present ideologically similar approaches are widely used to control spam.

  18. Nuclear mass predictions for the crustal composition of neutron stars: A Bayesian neural network approach

    Utama, R.; Piekarewicz, J.; Prosper, H. B.


    Background: Besides their intrinsic nuclear-structure value, nuclear mass models are essential for astrophysical applications, such as r -process nucleosynthesis and neutron-star structure. Purpose: To overcome the intrinsic limitations of existing "state-of-the-art" mass models through a refinement based on a Bayesian neural network (BNN) formalism. Methods: A novel BNN approach is implemented with the goal of optimizing mass residuals between theory and experiment. Results: A significant improvement (of about 40%) in the mass predictions of existing models is obtained after BNN refinement. Moreover, these improved results are now accompanied by proper statistical errors. Finally, by constructing a "world average" of these predictions, a mass model is obtained that is used to predict the composition of the outer crust of a neutron star. Conclusions: The power of the Bayesian neural network method has been successfully demonstrated by a systematic improvement in the accuracy of the predictions of nuclear masses. Extension to other nuclear observables is a natural next step that is currently under investigation.

  19. Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat

    Okut Hayrettin


    Full Text Available Abstract Background In the study of associations between genomic data and complex phenotypes there may be relationships that are not amenable to parametric statistical modeling. Such associations have been investigated mainly using single-marker and Bayesian linear regression models that differ in their distributions, but that assume additive inheritance while ignoring interactions and non-linearity. When interactions have been included in the model, their effects have entered linearly. There is a growing interest in non-parametric methods for predicting quantitative traits based on reproducing kernel Hilbert spaces regressions on markers and radial basis functions. Artificial neural networks (ANN provide an alternative, because these act as universal approximators of complex functions and can capture non-linear relationships between predictors and responses, with the interplay among variables learned adaptively. ANNs are interesting candidates for analysis of traits affected by cryptic forms of gene action. Results We investigated various Bayesian ANN architectures using for predicting phenotypes in two data sets consisting of milk production in Jersey cows and yield of inbred lines of wheat. For the Jerseys, predictor variables were derived from pedigree and molecular marker (35,798 single nucleotide polymorphisms, SNPS information on 297 individually cows. The wheat data represented 599 lines, each genotyped with 1,279 markers. The ability of predicting fat, milk and protein yield was low when using pedigrees, but it was better when SNPs were employed, irrespective of the ANN trained. Predictive ability was even better in wheat because the trait was a mean, as opposed to an individual phenotype in cows. Non-linear neural networks outperformed a linear model in predictive ability in both data sets, but more clearly in wheat. Conclusion Results suggest that neural networks may be useful for predicting complex traits using high

  20. Technical note: An R package for fitting Bayesian regularized neural networks with applications in animal breeding.

    Pérez-Rodríguez, P; Gianola, D; Weigel, K A; Rosa, G J M; Crossa, J


    In recent years, several statistical models have been developed for predicting genetic values for complex traits using information on dense molecular markers, pedigrees, or both. These models include, among others, the Bayesian regularized neural networks (BRNN) that have been widely used in prediction problems in other fields of application and, more recently, for genome-enabled prediction. The R package described here (brnn) implements BRNN models and extends these to include both additive and dominance effects. The implementation takes advantage of multicore architectures via a parallel computing approach using openMP (Open Multiprocessing) for the computations. This note briefly describes the classes of models that can be fitted using the brnn package, and it also illustrates its use through several real examples. PMID:23658327

  1. Bayesian model selection applied to artificial neural networks used for water resources modeling

    Kingston, Greer B.; Maier, Holger R.; Lambert, Martin F.


    Artificial neural networks (ANNs) have proven to be extremely valuable tools in the field of water resources engineering. However, one of the most difficult tasks in developing an ANN is determining the optimum level of complexity required to model a given problem, as there is no formal systematic model selection method. This paper presents a Bayesian model selection (BMS) method for ANNs that provides an objective approach for comparing models of varying complexity in order to select the most appropriate ANN structure. The approach uses Markov Chain Monte Carlo posterior simulations to estimate the evidence in favor of competing models and, in this study, three known methods for doing this are compared in terms of their suitability for being incorporated into the proposed BMS framework for ANNs. However, it is acknowledged that it can be particularly difficult to accurately estimate the evidence of ANN models. Therefore, the proposed BMS approach for ANNs incorporates a further check of the evidence results by inspecting the marginal posterior distributions of the hidden-to-output layer weights, which unambiguously indicate any redundancies in the hidden layer nodes. The fact that this check is available is one of the greatest advantages of the proposed approach over conventional model selection methods, which do not provide such a test and instead rely on the modeler's subjective choice of selection criterion. The advantages of a total Bayesian approach to ANN development, including training and model selection, are demonstrated on two synthetic and one real world water resources case study.

  2. Bayesian Neural Word Embedding

    Barkan, Oren


    Recently, several works in the domain of natural language processing presented successful methods for word embedding. Among them, the Skip-gram (SG) with negative sampling, known also as Word2Vec, advanced the state-of-the-art of various linguistics tasks. In this paper, we propose a scalable Bayesian neural word embedding algorithm that can be beneficial to general item similarity tasks as well. The algorithm relies on a Variational Bayes solution for the SG objective and a detailed step by ...

  3. Assessing Vermont's stream health and biological integrity using artificial neural networks and Bayesian methods

    Rizzo, D. M.; Fytilis, N.; Stevens, L.


    Environmental managers are increasingly required to monitor and forecast long-term effects and vulnerability of biophysical systems to human-generated stresses. Ideally, a study involving both physical and biological assessments conducted concurrently (in space and time) could provide a better understanding of the mechanisms and complex relationships. However, costs and resources associated with monitoring the complex linkages between the physical, geomorphic and habitat conditions and the biological integrity of stream reaches are prohibitive. Researchers have used classification techniques to place individual streams and rivers into a broader spatial context (hydrologic or health condition). Such efforts require environmental managers to gather multiple forms of information - quantitative, qualitative and subjective. We research and develop a novel classification tool that combines self-organizing maps with a Naïve Bayesian classifier to direct resources to stream reaches most in need. The Vermont Agency of Natural Resources has developed and adopted protocols for physical stream geomorphic and habitat assessments throughout the state of Vermont. Separate from these assessments, the Vermont Department of Environmental Conservation monitors the biological communities and the water quality in streams. Our initial hypothesis is that the geomorphic reach assessments and water quality data may be leveraged to reduce error and uncertainty associated with predictions of biological integrity and stream health. We test our hypothesis using over 2500 Vermont stream reaches (~1371 stream miles) assessed by the two agencies. In the development of this work, we combine a Naïve Bayesian classifier with a modified Kohonen Self-Organizing Map (SOM). The SOM is an unsupervised artificial neural network that autonomously analyzes inherent dataset properties using input data only. It is typically used to cluster data into similar categories when a priori classes do not exist. The

  4. Application of Bayesian Neural Networks to Energy Reconstruction in EAS Experiments for ground-based TeV Astrophysics

    Bai, Ying; Lan, JieQin; Gao, WeiWei


    A toy detector array has been designed to simulate the detection of cosmic rays in Extended Air Shower(EAS) Experiments for ground-based TeV Astrophysics. The primary energies of protons from the Monte-Carlo simulation have been reconstructed by the algorithm of Bayesian neural networks (BNNs) and a standard method like the LHAASO experiment\\cite{lhaaso-ma}, respectively. The result of the energy reconstruction using BNNs has been compared with the one using the standard method. Compared to the standard method, the energy resolutions are significantly improved using BNNs. And the improvement is more obvious for the high energy protons than the low energy ones.

  5. Application of Bayesian neural networks to energy reconstruction in EAS experiments for ground-based TeV astrophysics

    Bai, Y.; Xu, Y.; Pan, J.; Lan, J. Q.; Gao, W. W.


    A toy detector array is designed to detect a shower generated by the interaction between a TeV cosmic ray and the atmosphere. In the present paper, the primary energies of showers detected by the detector array are reconstructed with the algorithm of Bayesian neural networks (BNNs) and a standard method like the LHAASO experiment [1], respectively. Compared to the standard method, the energy resolutions are significantly improved using the BNNs. And the improvement is more obvious for the high energy showers than the low energy ones.

  6. Assessing uncertainty in climate change impacts on water resources: Bayesian neural network approach

    Climate change impact studies on water resources have so far provided results difficult to use for policy decision and planning of adaptation measures because of the lack of robust uncertainty estimates. There are various sources of uncertainty due to the global circulation models (GCMs) or the regional climate models (RCMs), the emission scenarios, the downscaling techniques, and the hydrological models. The estimation of the overall impact of those uncertainties on the future streamflow or reservoir inflow simulations at the watershed scale remains a difficult and challenging task. The use of multi-model super-ensembles in order to capture the wide range of uncertainties is cumbersome and requires large computational and human resources. As an alternative, a Bayesian Neural Network (BNN) approach is proposed as an effective hydrologic modeling tool for simulating future flows with uncertainty estimates. The BNN model is used with two versions of Canadian GCMs (CGCM1 and CGCM2) with two emission scenarios (SRES B2 and IPCC IS92a), and with one well established statistical downscaling model (SDSM) to simulate daily river flow and reservoir inflow in the Serpent River and the Chute-du-Diable watersheds in northern Quebec. It is found that the 95% uncertainty bands of the BNN mean ensemble flow (i.e. flow simulated using the mean ensemble of downscaled meteorological variables) is capable of encompassing all other possible flows corresponding to various individual downscaled meteorological ensembles whatever the CGCM and the emission scenario used. Specifically, this indicates that the BNN model confidence intervals are capable of including all possible flow variations due to various ensembles of downscaled meteorological variables from two different CGCMs and emission scenarios. Furthermore, the confidence limits of the BNN model also encompasses the flows simulated using another conceptual hydrologic model (namely HBV) whatever the GCM and the emission scenario

  7. Hierarchical Bayesian Model Averaging for Non-Uniqueness and Uncertainty Analysis of Artificial Neural Networks

    Fijani, E.; Chitsazan, N.; Nadiri, A.; Tsai, F. T.; Asghari Moghaddam, A.


    Artificial Neural Networks (ANNs) have been widely used to estimate concentration of chemicals in groundwater systems. However, estimation uncertainty is rarely discussed in the literature. Uncertainty in ANN output stems from three sources: ANN inputs, ANN parameters (weights and biases), and ANN structures. Uncertainty in ANN inputs may come from input data selection and/or input data error. ANN parameters are naturally uncertain because they are maximum-likelihood estimated. ANN structure is also uncertain because there is no unique ANN model given a specific case. Therefore, multiple plausible AI models are generally resulted for a study. One might ask why good models have to be ignored in favor of the best model in traditional estimation. What is the ANN estimation variance? How do the variances from different ANN models accumulate to the total estimation variance? To answer these questions we propose a Hierarchical Bayesian Model Averaging (HBMA) framework. Instead of choosing one ANN model (the best ANN model) for estimation, HBMA averages outputs of all plausible ANN models. The model weights are based on the evidence of data. Therefore, the HBMA avoids overconfidence on the single best ANN model. In addition, HBMA is able to analyze uncertainty propagation through aggregation of ANN models in a hierarchy framework. This method is applied for estimation of fluoride concentration in the Poldasht plain and the Bazargan plain in Iran. Unusually high fluoride concentration in the Poldasht and Bazargan plains has caused negative effects on the public health. Management of this anomaly requires estimation of fluoride concentration distribution in the area. The results show that the HBMA provides a knowledge-decision-based framework that facilitates analyzing and quantifying ANN estimation uncertainties from different sources. In addition HBMA allows comparative evaluation of the realizations for each source of uncertainty by segregating the uncertainty sources in

  8. The classification of oximetry signals using Bayesian neural networks to assist in the detection of obstructive sleep apnoea syndrome

    In the present study, multilayer perceptron (MLP) neural networks were applied to help in the diagnosis of obstructive sleep apnoea syndrome (OSAS). Oxygen saturation (SaO2) recordings from nocturnal pulse oximetry were used for this purpose. We performed time and spectral analysis of these signals to extract 14 features related to OSAS. The performance of two different MLP classifiers was compared: maximum likelihood (ML) and Bayesian (BY) MLP networks. A total of 187 subjects suspected of suffering from OSAS took part in the study. Their SaO2 signals were divided into a training set with 74 recordings and a test set with 113 recordings. BY-MLP networks achieved the best performance on the test set with 85.58% accuracy (87.76% sensitivity and 82.39% specificity). These results were substantially better than those provided by ML-MLP networks, which were affected by overfitting and achieved an accuracy of 76.81% (86.42% sensitivity and 62.83% specificity). Our results suggest that the Bayesian framework is preferred to implement our MLP classifiers. The proposed BY-MLP networks could be used for early OSAS detection. They could contribute to overcome the difficulties of nocturnal polysomnography (PSG) and thus reduce the demand for these studies

  9. Are Student Evaluations of Teaching Effectiveness Valid for Measuring Student Learning Outcomes in Business Related Classes? A Neural Network and Bayesian Analyses

    Galbraith, Craig S.; Merrill, Gregory B.; Kline, Doug M.


    In this study we investigate the underlying relational structure between student evaluations of teaching effectiveness (SETEs) and achievement of student learning outcomes in 116 business related courses. Utilizing traditional statistical techniques, a neural network analysis and a Bayesian data reduction and classification algorithm, we find…

  10. A hybrid approach to monthly streamflow forecasting: Integrating hydrological model outputs into a Bayesian artificial neural network

    Humphrey, Greer B.; Gibbs, Matthew S.; Dandy, Graeme C.; Maier, Holger R.


    Monthly streamflow forecasts are needed to support water resources decision making in the South East of South Australia, where baseflow represents a significant proportion of the total streamflow and soil moisture and groundwater are important predictors of runoff. To address this requirement, the utility of a hybrid monthly streamflow forecasting approach is explored, whereby simulated soil moisture from the GR4J conceptual rainfall-runoff model is used to represent initial catchment conditions in a Bayesian artificial neural network (ANN) statistical forecasting model. To assess the performance of this hybrid forecasting method, a comparison is undertaken of the relative performances of the Bayesian ANN, the GR4J conceptual model and the hybrid streamflow forecasting approach for producing 1-month ahead streamflow forecasts at three key locations in the South East of South Australia. Particular attention is paid to the quantification of uncertainty in each of the forecast models and the potential for reducing forecast uncertainty by using the hybrid approach is considered. Case study results suggest that the hybrid models developed in this study are able to take advantage of the complementary strengths of both the ANN models and the GR4J conceptual models. This was particularly the case when forecasting high flows, where the hybrid models were shown to outperform the two individual modelling approaches in terms of the accuracy of the median forecasts, as well as reliability and resolution of the forecast distributions. In addition, the forecast distributions generated by the hybrid models were up to 8 times more precise than those based on climatology; thus, providing a significant improvement on the information currently available to decision makers.

  11. Neural Networks

    Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

  12. Study of Single Top Quark Production Using Bayesian Neural Networks With D0 Detector at the Tevatron

    Joshi, Jyoti [Panjab Univ., Chandigarh (India)


    Top quark, the heaviest and most intriguing among the six known quarks, can be created via two independent production mechanisms in {\\pp} collisions. The primary mode, strong {\\ttbar} pair production from a $gtt$ vertex, was used by the {\\d0} and CDF collaborations to establish the existence of the top quark in March 1995. The second mode is the electroweak production of a single top quark or antiquark, which has been observed recently in March 2009. Since single top quarks are produced at hadron colliders through a $Wtb$ vertex, thereby provide a direct probe of the nature of $Wtb$ coupling and of the Cabibbo-Kobayashi-Maskawa matrix element, $V_{tb}$. So this mechanism provides a sensitive probe for several, standard model and beyond standard model, parameters such as anomalous $Wtb$ couplings. In this thesis, we measure the cross section of the electroweak produced top quark in three different production modes, $s+t$, $s$ and $t$-channels using a technique based on the Bayesian neural networks. This technique is applied for analysis of the 5.4 $fb^{-1}$ of data collected by the {\\d0} detector. From a comparison of the Bayesian neural networks discriminants between data and the signal-background model using Bayesian statistics, the cross sections of the top quark produced through the electroweak mechanism have been measured as: \\[\\sigma(p\\bar{p}→tb+X,tqb+X) = 3.11^{+0.77}_{-0.71}\\;\\rm pb\\] \\[\\sigma(p\\bar{p}→tb+X) = 0.72^{+0.44}_{-0.43}\\;\\rm pb\\] \\[\\sigma(p\\bar{p}→tqb+X) = 2.92^{+0.87}_{-0.73}\\;\\rm pb\\] % The $s+t$-channel has a gaussian significance of $4.7\\sigma$, the $s$-channel $0.9\\sigma$ and the $t$-channel~$4.7\\sigma$. The results are consistent with the standard model predictions within one standard deviation. By combining these results with the results for two other analyses (using different MVA techniques) improved results \\[\\sigma(p\\bar{p}→tb+X,tqb+X) = 3.43^{+0.73}_{-0.74}\\;\\rm pb\\] \\[\\sigma

  13. Topographic factor analysis: a Bayesian model for inferring brain networks from neural data.

    Jeremy R Manning

    Full Text Available The neural patterns recorded during a neuroscientific experiment reflect complex interactions between many brain regions, each comprising millions of neurons. However, the measurements themselves are typically abstracted from that underlying structure. For example, functional magnetic resonance imaging (fMRI datasets comprise a time series of three-dimensional images, where each voxel in an image (roughly reflects the activity of the brain structure(s-located at the corresponding point in space-at the time the image was collected. FMRI data often exhibit strong spatial correlations, whereby nearby voxels behave similarly over time as the underlying brain structure modulates its activity. Here we develop topographic factor analysis (TFA, a technique that exploits spatial correlations in fMRI data to recover the underlying structure that the images reflect. Specifically, TFA casts each brain image as a weighted sum of spatial functions. The parameters of those spatial functions, which may be learned by applying TFA to an fMRI dataset, reveal the locations and sizes of the brain structures activated while the data were collected, as well as the interactions between those structures.

  14. Phase Transitions of Neural Networks

    Kinzel, Wolfgang


    The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.

  15. Neural networks

    Vajda, Igor; Grim, Jiří

    Oxford : Eolss Publishers-UNESCO, 2008 - (Parra-Luna, F.), s. 224-248 ISBN 978-1-84826-654-4. - (Encyclopedia of Life Support Systems. Volume III) R&D Projects: GA ČR GA102/07/1594 Institutional research plan: CEZ:AV0Z10750506 Keywords : neural networks * probabilistic approach Subject RIV: BD - Theory of Information science and cybernetics .pdf

  16. Adaptive Dynamic Bayesian Networks

    Ng, B M


    A discrete-time Markov process can be compactly modeled as a dynamic Bayesian network (DBN)--a graphical model with nodes representing random variables and directed edges indicating causality between variables. Each node has a probability distribution, conditional on the variables represented by the parent nodes. A DBN's graphical structure encodes fixed conditional dependencies between variables. But in real-world systems, conditional dependencies between variables may be unknown a priori or may vary over time. Model errors can result if the DBN fails to capture all possible interactions between variables. Thus, we explore the representational framework of adaptive DBNs, whose structure and parameters can change from one time step to the next: a distribution's parameters and its set of conditional variables are dynamic. This work builds on recent work in nonparametric Bayesian modeling, such as hierarchical Dirichlet processes, infinite-state hidden Markov networks and structured priors for Bayes net learning. In this paper, we will explain the motivation for our interest in adaptive DBNs, show how popular nonparametric methods are combined to formulate the foundations for adaptive DBNs, and present preliminary results.

  17. Neural Networks and Photometric Redshifts

    Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo


    We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy...

  18. Bayesian Networks and Influence Diagrams

    Kjærulff, Uffe Bro; Madsen, Anders Læsø

     Probabilistic networks, also known as Bayesian networks and influence diagrams, have become one of the most promising technologies in the area of applied artificial intelligence, offering intuitive, efficient, and reliable methods for diagnosis, prediction, decision making, classification......, troubleshooting, and data mining under uncertainty. Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis provides a comprehensive guide for practitioners who wish to understand, construct, and analyze intelligent systems for decision support based on probabilistic networks. Intended...

  19. Neuronanatomy, neurology and Bayesian networks

    Bielza Lozoya, Maria Concepcion


    Bayesian networks are data mining models with clear semantics and a sound theoretical foundation. In this keynote talk we will pinpoint a number of neuroscience problems that can be addressed using Bayesian networks. In neuroanatomy, we will show computer simulation models of dendritic trees and classification of neuron types, both based on morphological features. In neurology, we will present the search for genetic biomarkers in Alzheimer's disease and the prediction of health-related qualit...

  20. Control of Complex Systems Using Bayesian Networks and Genetic Algorithm

    Marwala, Tshilidzi


    A method based on Bayesian neural networks and genetic algorithm is proposed to control the fermentation process. The relationship between input and output variables is modelled using Bayesian neural network that is trained using hybrid Monte Carlo method. A feedback loop based on genetic algorithm is used to change input variables so that the output variables are as close to the desired target as possible without the loss of confidence level on the prediction that the neural network gives. The proposed procedure is found to reduce the distance between the desired target and measured outputs significantly.

  1. Neural networks and statistical learning

    Du, Ke-Lin


    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...

  2. Fuzzy Naive Bayesian for constructing regulated network with weights.

    Zhou, Xi Y; Tian, Xue W; Lim, Joon S


    In the data mining field, classification is a very crucial technology, and the Bayesian classifier has been one of the hotspots in classification research area. However, assumptions of Naive Bayesian and Tree Augmented Naive Bayesian (TAN) are unfair to attribute relations. Therefore, this paper proposes a new algorithm named Fuzzy Naive Bayesian (FNB) using neural network with weighted membership function (NEWFM) to extract regulated relations and weights. Then, we can use regulated relations and weights to construct a regulated network. Finally, we will classify the heart and Haberman datasets by the FNB network to compare with experiments of Naive Bayesian and TAN. The experiment results show that the FNB has a higher classification rate than Naive Bayesian and TAN. PMID:26405944

  3. Projection of future climate change conditions using IPCC simulations, neural networks and Bayesian statistics. Part 2: Precipitation mean state and seasonal cycle in South America

    Boulanger, Jean-Philippe; Martinez, Fernando; Segura, Enrique C.


    Evaluating the response of climate to greenhouse gas forcing is a major objective of the climate community, and the use of large ensemble of simulations is considered as a significant step toward that goal. The present paper thus discusses a new methodology based on neural network to mix ensemble of climate model simulations. Our analysis consists of one simulation of seven Atmosphere Ocean Global Climate Models, which participated in the IPCC Project and provided at least one simulation for the twentieth century (20c3m) and one simulation for each of three SRES scenarios: A2, A1B and B1. Our statistical method based on neural networks and Bayesian statistics computes a transfer function between models and observations. Such a transfer function was then used to project future conditions and to derive what we would call the optimal ensemble combination for twenty-first century climate change projections. Our approach is therefore based on one statement and one hypothesis. The statement is that an optimal ensemble projection should be built by giving larger weights to models, which have more skill in representing present climate conditions. The hypothesis is that our method based on neural network is actually weighting the models that way. While the statement is actually an open question, which answer may vary according to the region or climate signal under study, our results demonstrate that the neural network approach indeed allows to weighting models according to their skills. As such, our method is an improvement of existing Bayesian methods developed to mix ensembles of simulations. However, the general low skill of climate models in simulating precipitation mean climatology implies that the final projection maps (whatever the method used to compute them) may significantly change in the future as models improve. Therefore, the projection results for late twenty-first century conditions are presented as possible projections based on the “state-of-the-art” of

  4. Bayesian Networks and Influence Diagrams

    Kjærulff, Uffe Bro; Madsen, Anders Læsø

    Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis, Second Edition, provides a comprehensive guide for practitioners who wish to understand, construct, and analyze intelligent systems for decision support based on probabilistic networks. This new edition contains six new...

  5. Projection of future climate change conditions using IPCC simulations, neural networks and Bayesian statistics. Part 2: Precipitation mean state and seasonal cycle in South America

    Boulanger, Jean-Philippe [LODYC, UMR CNRS/IRD/UPMC, Tour 45-55/Etage 4/Case 100, UPMC, Paris Cedex 05 (France); University of Buenos Aires, Departamento de Ciencias de la Atmosfera y los Oceanos, Facultad de Ciencias Exactas y Naturales, Buenos Aires (Argentina); Martinez, Fernando; Segura, Enrique C. [University of Buenos Aires, Departamento de Computacion, Facultad de Ciencias Exactas y Naturales, Buenos Aires (Argentina)


    Evaluating the response of climate to greenhouse gas forcing is a major objective of the climate community, and the use of large ensemble of simulations is considered as a significant step toward that goal. The present paper thus discusses a new methodology based on neural network to mix ensemble of climate model simulations. Our analysis consists of one simulation of seven Atmosphere-Ocean Global Climate Models, which participated in the IPCC Project and provided at least one simulation for the twentieth century (20c3m) and one simulation for each of three SRES scenarios: A2, A1B and B1. Our statistical method based on neural networks and Bayesian statistics computes a transfer function between models and observations. Such a transfer function was then used to project future conditions and to derive what we would call the optimal ensemble combination for twenty-first century climate change projections. Our approach is therefore based on one statement and one hypothesis. The statement is that an optimal ensemble projection should be built by giving larger weights to models, which have more skill in representing present climate conditions. The hypothesis is that our method based on neural network is actually weighting the models that way. While the statement is actually an open question, which answer may vary according to the region or climate signal under study, our results demonstrate that the neural network approach indeed allows to weighting models according to their skills. As such, our method is an improvement of existing Bayesian methods developed to mix ensembles of simulations. However, the general low skill of climate models in simulating precipitation mean climatology implies that the final projection maps (whatever the method used to compute them) may significantly change in the future as models improve. Therefore, the projection results for late twenty-first century conditions are presented as possible projections based on the &apos

  6. Bayesian modeling and classification of neural signals

    Lewicki, Michael S.


    Signal processing and classification algorithms often have limited applicability resulting from an inaccurate model of the signal's underlying structure. We present here an efficient, Bayesian algorithm for modeling a signal composed of the superposition of brief, Poisson-distributed functions. This methodology is applied to the specific problem of modeling and classifying extracellular neural waveforms which are composed of a superposition of an unknown number of action potentials CAPs). ...

  7. Bayesian networks and food security - An introduction

    Stein, A.


    This paper gives an introduction to Bayesian networks. Networks are defined and put into a Bayesian context. Directed acyclical graphs play a crucial role here. Two simple examples from food security are addressed. Possible uses of Bayesian networks for implementation and further use in decision sup

  8. Holographic neural networks

    Manger, R


    Holographic neural networks are a new and promising type of artificial neural networks. This article gives an overview of the holographic neural technology and its possibilities. The theoretical principles of holographic networks are first reviewed. Then, some other papers are presented, where holographic networks have been applied or experimentally evaluated. A case study dealing with currency exchange rate prediction is described in more detail.

  9. Bayesian Network--Response Regression

    WANG, LU; Durante, Daniele; Dunson, David B.


    There is an increasing interest in learning how human brain networks vary with continuous traits (e.g., personality, cognitive abilities, neurological disorders), but flexible procedures to accomplish this goal are limited. We develop a Bayesian semiparametric model, which combines low-rank factorizations and Gaussian process priors to allow flexible shifts of the conditional expectation for a network-valued random variable across the feature space, while including subject-specific random eff...

  10. Plug & Play object oriented Bayesian networks

    Bangsø, Olav; Flores, J.; Jensen, Finn Verner


    Object oriented Bayesian networks have proven themselves useful in recent years. The idea of applying an object oriented approach to Bayesian networks has extended their scope to larger domains that can be divided into autonomous but interrelated entities. Object oriented Bayesian networks have...... been shown to be quite suitable for dynamic domains as well. However, processing object oriented Bayesian networks in practice does not take advantage of their modular structure. Normally the object oriented Bayesian network is transformed into a Bayesian network and, inference is performed...... by constructing a junction tree from this network. In this paper we propose a method for translating directly from object oriented Bayesian networks to junction trees, avoiding the intermediate translation. We pursue two main purposes: firstly, to maintain the original structure organized in an instance tree...

  11. Linear and nonlinear modeling of antifungal activity of some heterocyclic ring derivatives using multiple linear regression and Bayesian-regularized neural networks.

    Caballero, Julio; Fernández, Michael


    Antifungal activity was modeled for a set of 96 heterocyclic ring derivatives (2,5,6-trisubstituted benzoxazoles, 2,5-disubstituted benzimidazoles, 2-substituted benzothiazoles and 2-substituted oxazolo(4,5-b)pyridines) using multiple linear regression (MLR) and Bayesian-regularized artificial neural network (BRANN) techniques. Inhibitory activity against Candida albicans (log(1/C)) was correlated with 3D descriptors encoding the chemical structures of the heterocyclic compounds. Training and test sets were chosen by means of k-Means Clustering. The most appropriate variables for linear and nonlinear modeling were selected using a genetic algorithm (GA) approach. In addition to the MLR equation (MLR-GA), two nonlinear models were built, model BRANN employing the linear variable subset and an optimum model BRANN-GA obtained by a hybrid method that combined BRANN and GA approaches (BRANN-GA). The linear model fit the training set (n = 80) with r2 = 0.746, while BRANN and BRANN-GA gave higher values of r2 = 0.889 and r2 = 0.937, respectively. Beyond the improvement of training set fitting, the BRANN-GA model was superior to the others by being able to describe 87% of test set (n = 16) variance in comparison with 78 and 81% the MLR-GA and BRANN models, respectively. Our quantitative structure-activity relationship study suggests that the distributions of atomic mass, volume and polarizability have relevant relationships with the antifungal potency of the compounds studied. Furthermore, the ability of the six variables selected nonlinearly to differentiate the data was demonstrated when the total data set was well distributed in a Kohonen self-organizing neural network (KNN). PMID:16205958

  12. Inference in hybrid Bayesian networks

    Lanseth, Helge; Nielsen, Thomas Dyhre; Rumí, Rafael;


    and reliability block diagrams). However, limitations in the BNs' calculation engine have prevented BNs from becoming equally popular for domains containing mixtures of both discrete and continuous variables (so-called hybrid domains). In this paper we focus on these difficulties, and summarize some of the last...... decade's research on inference in hybrid Bayesian networks. The discussions are linked to an example model for estimating human reliability....

  13. Space Shuttle RTOS Bayesian Network

    Morris, A. Terry; Beling, Peter A.


    With shrinking budgets and the requirements to increase reliability and operational life of the existing orbiter fleet, NASA has proposed various upgrades for the Space Shuttle that are consistent with national space policy. The cockpit avionics upgrade (CAU), a high priority item, has been selected as the next major upgrade. The primary functions of cockpit avionics include flight control, guidance and navigation, communication, and orbiter landing support. Secondary functions include the provision of operational services for non-avionics systems such as data handling for the payloads and caution and warning alerts to the crew. Recently, a process to selection the optimal commercial-off-the-shelf (COTS) real-time operating system (RTOS) for the CAU was conducted by United Space Alliance (USA) Corporation, which is a joint venture between Boeing and Lockheed Martin, the prime contractor for space shuttle operations. In order to independently assess the RTOS selection, NASA has used the Bayesian network-based scoring methodology described in this paper. Our two-stage methodology addresses the issue of RTOS acceptability by incorporating functional, performance and non-functional software measures related to reliability, interoperability, certifiability, efficiency, correctness, business, legal, product history, cost and life cycle. The first stage of the methodology involves obtaining scores for the various measures using a Bayesian network. The Bayesian network incorporates the causal relationships between the various and often competing measures of interest while also assisting the inherently complex decision analysis process with its ability to reason under uncertainty. The structure and selection of prior probabilities for the network is extracted from experts in the field of real-time operating systems. Scores for the various measures are computed using Bayesian probability. In the second stage, multi-criteria trade-off analyses are performed between the scores

  14. Chaotic diagonal recurrent neural network

    Wang Xing-Yuan; Zhang Yi


    We propose a novel neural network based on a diagonal recurrent neural network and chaos,and its structure andlearning algorithm are designed.The multilayer feedforward neural network,diagonal recurrent neural network,and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map.The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.

  15. Chaotic diagonal recurrent neural network

    We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)

  16. Quantum Inference on Bayesian Networks

    Yoder, Theodore; Low, Guang Hao; Chuang, Isaac


    Because quantum physics is naturally probabilistic, it seems reasonable to expect physical systems to describe probabilities and their evolution in a natural fashion. Here, we use quantum computation to speedup sampling from a graphical probability model, the Bayesian network. A specialization of this sampling problem is approximate Bayesian inference, where the distribution on query variables is sampled given the values e of evidence variables. Inference is a key part of modern machine learning and artificial intelligence tasks, but is known to be NP-hard. Classically, a single unbiased sample is obtained from a Bayesian network on n variables with at most m parents per node in time (nmP(e) - 1 / 2) , depending critically on P(e) , the probability the evidence might occur in the first place. However, by implementing a quantum version of rejection sampling, we obtain a square-root speedup, taking (n2m P(e) -1/2) time per sample. The speedup is the result of amplitude amplification, which is proving to be broadly applicable in sampling and machine learning tasks. In particular, we provide an explicit and efficient circuit construction that implements the algorithm without the need for oracle access.

  17. Neural Networks and Photometric Redshifts

    Tagliaferri, R; Andreon, S; Capozziello, S; Donalek, C; Giordano, G; Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo


    We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy of the results, turned out to be the most effective. In the best experiment, the implemented network reached an accuracy of 0.020 (interquartile error) in the range 0

  18. Nonparametric Bayesian Modeling of Complex Networks

    Schmidt, Mikkel Nørgaard; Mørup, Morten


    Modeling structure in complex networks using Bayesian nonparametrics makes it possible to specify flexible model structures and infer the adequate model complexity from the observed data. This article provides a gentle introduction to nonparametric Bayesian modeling of complex networks: Using...... for complex networks can be derived and point out relevant literature....

  19. Bayesian networks with applications in reliability analysis

    Langseth, Helge


    A common goal of the papers in this thesis is to propose, formalize and exemplify the use of Bayesian networks as a modelling tool in reliability analysis. The papers span work in which Bayesian networks are merely used as a modelling tool (Paper I), work where models are specially designed to utilize the inference algorithms of Bayesian networks (Paper II and Paper III), and work where the focus has been on extending the applicability of Bayesian networks to very large domains (Paper IV and ...

  20. Neural Networks: Implementations and Applications

    Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.


    Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas

  1. Evolution of neural networks

    Uršič, Aleš


    The goal of this work is construction of an artificial life model and simulation of organisms in an environment with food. Organisms survive if they find food successfuly. With evolution and learning organisms develop a neural network which enables that. First neural networks and their history are introduced with the basic concepts like a neuron model, a network, transfer functions, topologies and learning. I describe the backpropagation learning on multilayer feed forward network and dem...

  2. Compiling Relational Bayesian Networks for Exact Inference

    Jaeger, Manfred; Chavira, Mark; Darwiche, Adnan


    We describe a system for exact inference with relational Bayesian networks as defined in the publicly available \\primula\\ tool. The system is based on compiling propositional instances of relational Bayesian networks into arithmetic circuits and then performing online inference by evaluating and ...

  3. Compiling Relational Bayesian Networks for Exact Inference

    Jaeger, Manfred; Darwiche, Adnan; Chavira, Mark

    We describe in this paper a system for exact inference with relational Bayesian networks as defined in the publicly available PRIMULA tool. The system is based on compiling propositional instances of relational Bayesian networks into arithmetic circuits and then performing online inference by eva...

  4. An Intuitive Dashboard for Bayesian Network Inference

    Reddy, Vikas; Charisse Farr, Anna; Wu, Paul; Mengersen, Kerrie; Yarlagadda, Prasad K. D. V.


    Current Bayesian network software packages provide good graphical interface for users who design and develop Bayesian networks for various applications. However, the intended end-users of these networks may not necessarily find such an interface appealing and at times it could be overwhelming, particularly when the number of nodes in the network is large. To circumvent this problem, this paper presents an intuitive dashboard, which provides an additional layer of abstraction, enabling the end-users to easily perform inferences over the Bayesian networks. Unlike most software packages, which display the nodes and arcs of the network, the developed tool organises the nodes based on the cause-and-effect relationship, making the user-interaction more intuitive and friendly. In addition to performing various types of inferences, the users can conveniently use the tool to verify the behaviour of the developed Bayesian network. The tool has been developed using QT and SMILE libraries in C++.

  5. An Intuitive Dashboard for Bayesian Network Inference

    Current Bayesian network software packages provide good graphical interface for users who design and develop Bayesian networks for various applications. However, the intended end-users of these networks may not necessarily find such an interface appealing and at times it could be overwhelming, particularly when the number of nodes in the network is large. To circumvent this problem, this paper presents an intuitive dashboard, which provides an additional layer of abstraction, enabling the end-users to easily perform inferences over the Bayesian networks. Unlike most software packages, which display the nodes and arcs of the network, the developed tool organises the nodes based on the cause-and-effect relationship, making the user-interaction more intuitive and friendly. In addition to performing various types of inferences, the users can conveniently use the tool to verify the behaviour of the developed Bayesian network. The tool has been developed using QT and SMILE libraries in C++

  6. Bayesian networks in educational assessment

    Almond, Russell G; Steinberg, Linda S; Yan, Duanli; Williamson, David M


    Bayesian inference networks, a synthesis of statistics and expert systems, have advanced reasoning under uncertainty in medicine, business, and social sciences. This innovative volume is the first comprehensive treatment exploring how they can be applied to design and analyze innovative educational assessments. Part I develops Bayes nets’ foundations in assessment, statistics, and graph theory, and works through the real-time updating algorithm. Part II addresses parametric forms for use with assessment, model-checking techniques, and estimation with the EM algorithm and Markov chain Monte Carlo (MCMC). A unique feature is the volume’s grounding in Evidence-Centered Design (ECD) framework for assessment design. This “design forward” approach enables designers to take full advantage of Bayes nets’ modularity and ability to model complex evidentiary relationships that arise from performance in interactive, technology-rich assessments such as simulations. Part III describes ECD, situates Bayes nets as ...

  7. Hidden neural networks

    Krogh, Anders Stærmose; Riis, Søren Kamaric


    A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability...... parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum...... likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear...

  8. Neural networks for aircraft control

    Linse, Dennis


    Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

  9. Neural Network Ensembles

    Hansen, Lars Kai; Salamon, Peter


    We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....

  10. Learning Bayesian networks for discrete data

    Liang, Faming


    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.

  11. Critical Branching Neural Networks

    Kello, Christopher T.


    It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…

  12. Designing neural networks that process mean values of random variables

    We develop a class of neural networks derived from probabilistic models posed in the form of Bayesian networks. Making biologically and technically plausible assumptions about the nature of the probabilistic models to be represented in the networks, we derive neural networks exhibiting standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the relevant random variables, that can pool multiple sources of evidence, and that deal appropriately with ambivalent, inconsistent, or contradictory evidence. - Highlights: • High-level neural computations are specified by Bayesian belief networks of random variables. • Probability densities of random variables are encoded in activities of populations of neurons. • Top-down algorithm generates specific neural network implementation of given computation. • Resulting “neural belief networks” process mean values of random variables. • Such networks pool multiple sources of evidence and deal properly with inconsistent evidence

  13. Recurrent Neural Network Regularization

    Zaremba, Wojciech; Sutskever, Ilya; Vinyals, Oriol


    We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation.

  14. Deep Sequential Neural Network

    Denoyer, Ludovic; Gallinari, Patrick


    Neural Networks sequentially build high-level features through their successive layers. We propose here a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process. The resulting model is structured according to a DAG like architecture, so that a path from the root to a leaf node defines a sequence of transformations. Instead of c...

  15. The Future of Neural Networks

    Lakra, Sachin; T. V. Prasad; G. Ramakrishna


    The paper describes some recent developments in neural networks and discusses the applicability of neural networks in the development of a machine that mimics the human brain. The paper mentions a new architecture, the pulsed neural network that is being considered as the next generation of neural networks. The paper also explores the use of memristors in the development of a brain-like computer called the MoNETA. A new model, multi/infinite dimensional neural networks, are a recent developme...

  16. Neural Networks in Data Mining

    Priyanka Gaur


    The application of neural networks in the data mining is very wide. Although neural networks may have complex structure, long training time, and uneasily understandable representation of results, neural networks have high acceptance ability for noisy data and high accuracy and are preferable in data mining. In this paper the data mining based on neural networks is researched in detail, and the key technology and ways to achieve the data mining based on neural networks are also researched.

  17. Neural networks and graph theory

    许进; 保铮


    The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.

  18. The Diagnosis of Reciprocating Machinery by Bayesian Networks


    A Bayesian Network is a reasoning tool based on probability theory and has many advantages that other reasoning tools do not have. This paper discusses the basic theory of Bayesian networks and studies the problems in constructing Bayesian networks. The paper also constructs a Bayesian diagnosis network of a reciprocating compressor. The example helps us to draw a conclusion that Bayesian diagnosis networks can diagnose reciprocating machinery effectively.

  19. An introduction to Gaussian Bayesian networks.

    Grzegorczyk, Marco


    The extraction of regulatory networks and pathways from postgenomic data is important for drug -discovery and development, as the extracted pathways reveal how genes or proteins regulate each other. Following up on the seminal paper of Friedman et al. (J Comput Biol 7:601-620, 2000), Bayesian networks have been widely applied as a popular tool to this end in systems biology research. Their popularity stems from the tractability of the marginal likelihood of the network structure, which is a consistent scoring scheme in the Bayesian context. This score is based on an integration over the entire parameter space, for which highly expensive computational procedures have to be applied when using more complex -models based on differential equations; for example, see (Bioinformatics 24:833-839, 2008). This chapter gives an introduction to reverse engineering regulatory networks and pathways with Gaussian Bayesian networks, that is Bayesian networks with the probabilistic BGe scoring metric [see (Geiger and Heckerman 235-243, 1995)]. In the BGe model, the data are assumed to stem from a Gaussian distribution and a normal-Wishart prior is assigned to the unknown parameters. Gaussian Bayesian network methodology for analysing static observational, static interventional as well as dynamic (observational) time series data will be described in detail in this chapter. Finally, we apply these Bayesian network inference methods (1) to observational and interventional flow cytometry (protein) data from the well-known RAF pathway to evaluate the global network reconstruction accuracy of Bayesian network inference and (2) to dynamic gene expression time series data of nine circadian genes in Arabidopsis thaliana to reverse engineer the unknown regulatory network topology for this domain. PMID:20824469

  20. Fuzzy Functional Dependencies and Bayesian Networks

    LIU WeiYi(刘惟一); SONG Ning(宋宁)


    Bayesian networks have become a popular technique for representing and reasoning with probabilistic information. The fuzzy functional dependency is an important kind of data dependencies in relational databases with fuzzy values. The purpose of this paper is to set up a connection between these data dependencies and Bayesian networks. The connection is done through a set of methods that enable people to obtain the most information of independent conditions from fuzzy functional dependencies.

  1. Introduction to neural networks

    This lecture is a presentation of today's research in neural computation. Neural computation is inspired by knowledge from neuro-science. It draws its methods in large degree from statistical physics and its potential applications lie mainly in computer science and engineering. Neural networks models are algorithms for cognitive tasks, such as learning and optimization, which are based on concepts derived from research into the nature of the brain. The lecture first gives an historical presentation of neural networks development and interest in performing complex tasks. Then, an exhaustive overview of data management and networks computation methods is given: the supervised learning and the associative memory problem, the capacity of networks, the Perceptron networks, the functional link networks, the Madaline (Multiple Adalines) networks, the back-propagation networks, the reduced coulomb energy (RCE) networks, the unsupervised learning and the competitive learning and vector quantization. An example of application in high energy physics is given with the trigger systems and track recognition system (track parametrization, event selection and particle identification) developed for the CPLEAR experiment detectors from the LEAR at CERN. (J.S.). 56 refs., 20 figs., 1 tab., 1 appendix

  2. Hyperbolic Hopfield neural networks.

    Kobayashi, M


    In recent years, several neural networks using Clifford algebra have been studied. Clifford algebra is also called geometric algebra. Complex-valued Hopfield neural networks (CHNNs) are the most popular neural networks using Clifford algebra. The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs. Hyperbolic algebra is a Clifford algebra based on Lorentzian geometry. In this brief, a hyperbolic neuron is defined in a manner analogous to a phasor neuron, which is a typical complex-valued neuron model. HHNNs share common concepts with CHNNs, such as the angle and energy. However, HHNNs and CHNNs are different in several aspects. The states of hyperbolic neurons do not form a circle, and, therefore, the start and end states are not identical. In the quantized version, unlike complex-valued neurons, hyperbolic neurons have an infinite number of states. PMID:24808287

  3. Rule Extraction:Using Neural Networks or for Neural Networks?

    Zhi-Hua Zhou


    In the research of rule extraction from neural networks, fidelity describes how well the rules mimic the behavior of a neural network while accuracy describes how well the rules can be generalized. This paper identifies the fidelity-accuracy dilemma. It argues to distinguish rule extraction using neural networks and rule extraction for neural networks according to their different goals, where fidelity and accuracy should be excluded from the rule quality evaluation framework, respectively.

  4. Bayesian Network Models for Adaptive Testing

    Plajner, Martin; Vomlel, Jiří

    Achen: Sun SITE Central Europe, 2016 - (Agosta, J.; Carvalho, R.), s. 24-33. (CEUR Workshop Proceedings. Vol 1565). ISSN 1613-0073. [The Twelfth UAI Bayesian Modeling Applications Workshop (BMAW 2015). Amsterdam (NL), 16.07.2015] R&D Projects: GA ČR GA13-20012S Institutional support: RVO:67985556 Keywords : Bayesian networks * Computerized adaptive testing Subject RIV: JD - Computer Applications, Robotics

  5. Scaling Bayesian network discovery through incremental recovery

    Castelo, J.R.; Siebes, A.P.J.M.


    Bayesian networks are a type of graphical models that, e.g., allow one to analyze the interaction among the variables in a database. A well-known problem with the discovery of such models from a database is the ``problem of high-dimensionality''. That is, the discovery of a network from a database w

  6. Introduction to Artificial Neural Networks

    Larsen, Jan


    The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....

  7. Artificial neural network modelling

    Samarasinghe, Sandhya


    This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling. .

  8. Neural Networks and Micromechanics

    Kussul, Ernst; Baidyk, Tatiana; Wunsch, Donald C.

    The title of the book, "Neural Networks and Micromechanics," seems artificial. However, the scientific and technological developments in recent decades demonstrate a very close connection between the two different areas of neural networks and micromechanics. The purpose of this book is to demonstrate this connection. Some artificial intelligence (AI) methods, including neural networks, could be used to improve automation system performance in manufacturing processes. However, the implementation of these AI methods within industry is rather slow because of the high cost of conducting experiments using conventional manufacturing and AI systems. To lower the cost, we have developed special micromechanical equipment that is similar to conventional mechanical equipment but of much smaller size and therefore of lower cost. This equipment could be used to evaluate different AI methods in an easy and inexpensive way. The proved methods could be transferred to industry through appropriate scaling. In this book, we describe the prototypes of low cost microequipment for manufacturing processes and the implementation of some AI methods to increase precision, such as computer vision systems based on neural networks for microdevice assembly and genetic algorithms for microequipment characterization and the increase of microequipment precision.

  9. Generalized Adaptive Artificial Neural Networks

    Tawel, Raoul


    Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.

  10. Learning Bayesian Networks from Correlated Data

    Bae, Harold; Monti, Stefano; Montano, Monty; Steinberg, Martin H.; Perls, Thomas T.; Sebastiani, Paola


    Bayesian networks are probabilistic models that represent complex distributions in a modular way and have become very popular in many fields. There are many methods to build Bayesian networks from a random sample of independent and identically distributed observations. However, many observational studies are designed using some form of clustered sampling that introduces correlations between observations within the same cluster and ignoring this correlation typically inflates the rate of false positive associations. We describe a novel parameterization of Bayesian networks that uses random effects to model the correlation within sample units and can be used for structure and parameter learning from correlated data without inflating the Type I error rate. We compare different learning metrics using simulations and illustrate the method in two real examples: an analysis of genetic and non-genetic factors associated with human longevity from a family-based study, and an example of risk factors for complications of sickle cell anemia from a longitudinal study with repeated measures.

  11. Boltzmann learning of parameters in cellular neural networks

    Hansen, Lars Kai


    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 ...... unsupervised adaptation of an image segmentation cellular network. The learning rule is applied to adaptive segmentation of satellite imagery......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 by...

  12. Artificial Neural Network

    Kapil Nahar


    Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems. Ann’s, like people, learn by example.

  13. Implementing Neural Networks Efficiently

    Collobert, Ronan; Kavukcuoglu, Koray; Farabet, Clément; Montavon, Grégoire; Orr, Geneviève; Müller, K.-R.


    Neural networks and machine learning algorithms in general require a flexible environment where new algorithm prototypes and experiments can be set up as quickly as possible with best possible computational performance. To that end, we provide a new framework called Torch7, that is especially suited to achieve both of these competing goals. Torch7 is a versatile numeric computing framework and machine learning library that extends a very lightweight and powerful programming language Lua. Its ...

  14. Neural networks for triggering

    Denby, B. (Fermi National Accelerator Lab., Batavia, IL (USA)); Campbell, M. (Michigan Univ., Ann Arbor, MI (USA)); Bedeschi, F. (Istituto Nazionale di Fisica Nucleare, Pisa (Italy)); Chriss, N.; Bowers, C. (Chicago Univ., IL (USA)); Nesti, F. (Scuola Normale Superiore, Pisa (Italy))


    Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.

  15. Neural networks for triggering

    Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab

  16. Dynamic recurrent neural networks

    Pearlmutter, Barak A


    We survey learning algorithms for recurrent neural networks with hidden units and attempt to put the various techniques into a common framework. We discuss fixpoint learning algorithms, namely recurrent backpropagation and deterministic Boltzmann Machines, and non-fixpoint algorithms, namely backpropagation through time, Elman's history cutoff nets, and Jordan's output feedback architecture. Forward propagation, an online technique that uses adjoint equations, is also discussed. In many cases...

  17. Benchmarking dynamic Bayesian network structure learning algorithms

    Trabelsi, Ghada; Leray, Philippe; Ben Ayed, Mounir; Alimi, Adel


    Dynamic Bayesian Networks (DBNs) are probabilistic graphical models dedicated to modeling multivariate time series. Two-time slice BNs (2-TBNs) are the most current type of these models. Static BN structure learning is a well-studied domain. Many approaches have been proposed and the quality of these algorithms has been studied over a range of di erent standard networks and methods of evaluation. To the best of our knowledge, all studies about DBN structure learning use their own benchmarks a...

  18. Neural networks for damage identification

    Paez, T.L.; Klenke, S.E.


    Efforts to optimize the design of mechanical systems for preestablished use environments and to extend the durations of use cycles establish a need for in-service health monitoring. Numerous studies have proposed measures of structural response for the identification of structural damage, but few have suggested systematic techniques to guide the decision as to whether or not damage has occurred based on real data. Such techniques are necessary because in field applications the environments in which systems operate and the measurements that characterize system behavior are random. This paper investigates the use of artificial neural networks (ANNs) to identify damage in mechanical systems. Two probabilistic neural networks (PNNs) are developed and used to judge whether or not damage has occurred in a specific mechanical system, based on experimental measurements. The first PNN is a classical type that casts Bayesian decision analysis into an ANN framework; it uses exemplars measured from the undamaged and damaged system to establish whether system response measurements of unknown origin come from the former class (undamaged) or the latter class (damaged). The second PNN establishes the character of the undamaged system in terms of a kernel density estimator of measures of system response; when presented with system response measures of unknown origin, it makes a probabilistic judgment whether or not the data come from the undamaged population. The physical system used to carry out the experiments is an aerospace system component, and the environment used to excite the system is a stationary random vibration. The results of damage identification experiments are presented along with conclusions rating the effectiveness of the approaches.

  19. Bayesian Overlapping Community Detection in Dynamic Networks

    Ghorbani, Mahsa; Khodadadi, Ali


    Detecting community structures in social networks has gained considerable attention in recent years. However, lack of prior knowledge about the number of communities, and their overlapping nature have made community detection a challenging problem. Moreover, many of the existing methods only consider static networks, while most of real world networks are dynamic and evolve over time. Hence, finding consistent overlapping communities in dynamic networks without any prior knowledge about the number of communities is still an interesting open research problem. In this paper, we present an overlapping community detection method for dynamic networks called Dynamic Bayesian Overlapping Community Detector (DBOCD). DBOCD assumes that in every snapshot of network, overlapping parts of communities are dense areas and utilizes link communities instead of common node communities. Using Recurrent Chinese Restaurant Process and community structure of the network in the last snapshot, DBOCD simultaneously extracts the numbe...

  20. Bayesian network learning for natural hazard assessments

    Vogel, Kristin


    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

  1. Neural logic networks a new class of neural networks

    Heng, Teh Hoon


    This book is the first of a series of technical reports of a key research project of the Real-World Computing Program supported by the MITI of Japan.The main goal of the project is to model human intelligence by a special class of mathematical systems called neural logic networks.The book consists of three parts. Part 1 describes the general theory of neural logic networks and their potential applications. Part 2 discusses a new logic called Neural Logic which attempts to emulate more closely the logical thinking process of human. Part 3 studies the special features of neural logic networks wh

  2. Learning Bayesian networks using genetic algorithm

    Chen Fei; Wang Xiufeng; Rao Yimei


    A new method to evaluate the fitness of the Bayesian networks according to the observed data is provided. The main advantage of this criterion is that it is suitable for both the complete and incomplete cases while the others not.Moreover it facilitates the computation greatly. In order to reduce the search space, the notation of equivalent class proposed by David Chickering is adopted. Instead of using the method directly, the novel criterion, variable ordering, and equivalent class are combined,moreover the proposed mthod avoids some problems caused by the previous one. Later, the genetic algorithm which allows global convergence, lack in the most of the methods searching for Bayesian network is applied to search for a good model in thisspace. To speed up the convergence, the genetic algorithm is combined with the greedy algorithm. Finally, the simulation shows the validity of the proposed approach.

  3. Bayesian networks for enterprise risk assessment

    Bonafede, C E


    According to different typologies of activity and priority, risks can assume diverse meanings and it can be assessed in different ways. In general risk is measured in terms of a probability combination of an event (frequency) and its consequence (impact). To estimate the frequency and the impact (severity) historical data or expert opinions (either qualitative or quantitative data) are used. Moreover qualitative data must be converted in numerical values to be used in the model. In the case of enterprise risk assessment the considered risks are, for instance, strategic, operational, legal and of image, which many times are difficult to be quantified. So in most cases only expert data, gathered by scorecard approaches, are available for risk analysis. The Bayesian Network is a useful tool to integrate different information and in particular to study the risk's joint distribution by using data collected from experts. In this paper we want to show a possible approach for building a Bayesian networks in the parti...

  4. Software Health Management with Bayesian Networks

    Mengshoel, Ole; Schumann, JOhann


    Most modern aircraft as well as other complex machinery is equipped with diagnostics systems for its major subsystems. During operation, sensors provide important information about the subsystem (e.g., the engine) and that information is used to detect and diagnose faults. Most of these systems focus on the monitoring of a mechanical, hydraulic, or electromechanical subsystem of the vehicle or machinery. Only recently, health management systems that monitor software have been developed. In this paper, we will discuss our approach of using Bayesian networks for Software Health Management (SWHM). We will discuss SWHM requirements, which make advanced reasoning capabilities for the detection and diagnosis important. Then we will present our approach to using Bayesian networks for the construction of health models that dynamically monitor a software system and is capable of detecting and diagnosing faults.

  5. Distributed Bayesian Networks for User Modeling

    Tedesco, Roberto; Dolog, Peter; Nejdl, Wolfgang;


    The World Wide Web is a popular platform for providing eLearning applications to a wide spectrum of users. However – as users differ in their preferences, background, requirements, and goals – applications should provide personalization mechanisms. In the Web context, user models used by such...... adaptive applications are often partial fragments of an overall user model. The fragments have then to be collected and merged into a global user profile. In this paper we investigate and present algorithms able to cope with distributed, fragmented user models – based on Bayesian Networks – in the context...... mechanism efficiently combines distributed learner models without the need to exchange internal structure of local Bayesian networks, nor local evidence between the involved platforms....

  6. Centralized Bayesian reliability modelling with sensor networks

    Dedecius, Kamil; Sečkárová, Vladimíra


    Roč. 19, č. 5 (2013), s. 471-482. ISSN 1387-3954 R&D Projects: GA MŠk 7D12004 Grant ostatní: GA MŠk(CZ) SVV-265315 Keywords : Bayesian modelling * Sensor network * Reliability Subject RIV: BD - Theory of Information Impact factor: 0.984, year: 2013

  7. Characteristic imsets for learning Bayesian network structure

    Hemmecke, R.; Lindner, S.; Studený, Milan


    Roč. 53, č. 9 (2012), s. 1336-1349. ISSN 0888-613X R&D Projects: GA MŠk(CZ) 1M0572; GA ČR GA201/08/0539 Institutional support: RVO:67985556 Keywords : learning Bayesian network structure * essential graph * standard imset * characteristic imset * LP relaxation of a polytope Subject RIV: BA - General Mathematics Impact factor: 1.729, year: 2012

  8. Forming Object Concept Using Bayesian Network

    Nakamura, Tomoaki; Nagai, Takayuki


    This chapter hase discussed a novel framework for object understanding. Implementation of the proposed framework using Bayesian Network has been presented. Although the result given in this paper is preliminary one, we have shown that the system can form object concept by observing the performance by human hands. The on-line learning is left for the future works. Moreover the model should be extended so that it can represent the object usage and work objects.

  9. Improving Environmental Scanning Systems Using Bayesian Networks

    Simon Welter; Jörg H. Mayer; Reiner Quick


    As companies’ environment is becoming increasingly volatile, scanning systems gain in importance. We propose a hybrid process model for such systems' information gathering and interpretation tasks that combines quantitative information derived from regression analyses and qualitative knowledge from expert interviews. For the latter, we apply Bayesian networks. We derive the need for such a hybrid process model from a literature review. We lay out our model to find a suitable set of business e...

  10. Parameterized Complexity Results for Exact Bayesian Network Structure Learning

    Sebastian Ordyniak; Stefan Szeider


    Bayesian network structure learning is the notoriously difficult problem of discovering a Bayesian network that optimally represents a given set of training data. In this paper we study the computational worst-case complexity of exact Bayesian network structure learning under graph theoretic restrictions on the (directed) super-structure. The super-structure is an undirected graph that contains as subgraphs the skeletons of solution networks. We introduce the directed super-structure as a nat...

  11. Interacting neural networks.

    Metzler, R; Kinzel, W; Kanter, I


    Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random. PMID:11088736

  12. Analysis of neural networks

    Heiden, Uwe


    The purpose of this work is a unified and general treatment of activity in neural networks from a mathematical pOint of view. Possible applications of the theory presented are indica­ ted throughout the text. However, they are not explored in de­ tail for two reasons : first, the universal character of n- ral activity in nearly all animals requires some type of a general approach~ secondly, the mathematical perspicuity would suffer if too many experimental details and empirical peculiarities were interspersed among the mathematical investigation. A guide to many applications is supplied by the references concerning a variety of specific issues. Of course the theory does not aim at covering all individual problems. Moreover there are other approaches to neural network theory (see e.g. Poggio-Torre, 1978) based on the different lev­ els at which the nervous system may be viewed. The theory is a deterministic one reflecting the average be­ havior of neurons or neuron pools. In this respect the essay is writt...

  13. Application of Bayesian regularized BP neural network model for analysis of aquatic ecological data--A case study of chlorophyll-a prediction in Nanzui water area of Dongting Lake

    XU Min; ZENG Guang-ming; XU Xin-yi; HUANG Guo-he; SUN Wei; JIANG Xiao-yun


    Bayesian regularized BP neural network(BRBPNN) technique was applied in the chlorophyll-a prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS 11.0 software, the BRBPNN model was established between chlorophyll-a and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.00078426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll-a declined in the order of alga amount > secchi disc depth(SD) > electrical conductivity (EC) . Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-a concentration, total phosphorus(TP) and total nitrogen(TN) were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data(chlorophyll-a prediction) and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.

  14. Modeling operational risks of the nuclear industry with Bayesian networks

    Basically, planning a new industrial plant requires information on the industrial management, regulations, site selection, definition of initial and planned capacity, and on the estimation of the potential demand. However, this is far from enough to assure the success of an industrial enterprise. Unexpected and extremely damaging events may occur that deviates from the original plan. The so-called operational risks are not only in the system, equipment, process or human (technical or managerial) failures. They are also in intentional events such as frauds and sabotage, or extreme events like terrorist attacks or radiological accidents and even on public reaction to perceived environmental or future generation impacts. For the nuclear industry, it is a challenge to identify and to assess the operational risks and their various sources. Early identification of operational risks can help in preparing contingency plans, to delay the decision to invest or to approve a project that can, at an extreme, affect the public perception of the nuclear energy. A major problem in modeling operational risk losses is the lack of internal data that are essential, for example, to apply the loss distribution approach. As an alternative, methods that consider qualitative and subjective information can be applied, for example, fuzzy logic, neural networks, system dynamic or Bayesian networks. An advantage of applying Bayesian networks to model operational risk is the possibility to include expert opinions and variables of interest, to structure the model via causal dependencies among these variables, and to specify subjective prior and conditional probabilities distributions at each step or network node. This paper suggests a classification of operational risks in industry and discusses the benefits and obstacles of the Bayesian networks approach to model those risks. (author)

  15. Neural network applications in telecommunications

    Alspector, Joshua


    Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.

  16. Neural networks at the Tevatron

    This paper summarizes neural network applications at the Fermilab Tevatron, including the first online hardware application in high energy physics (muon tracking): the CDF and DO neural network triggers; offline quark/gluon discrimination at CDF; ND a new tool for top to multijets recognition at CDF

  17. Neural Networks for Optimal Control

    Sørensen, O.


    Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....

  18. Neural Networks for the Beginner.

    Snyder, Robin M.

    Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…

  19. Revealing ecological networks using Bayesian network inference algorithms.

    Milns, Isobel; Beale, Colin M; Smith, V Anne


    Understanding functional relationships within ecological networks can help reveal keys to ecosystem stability or fragility. Revealing these relationships is complicated by the difficulties of isolating variables or performing experimental manipulations within a natural ecosystem, and thus inferences are often made by matching models to observational data. Such models, however, require assumptions-or detailed measurements-of parameters such as birth and death rate, encounter frequency, territorial exclusion, and predation success. Here, we evaluate the use of a Bayesian network inference algorithm, which can reveal ecological networks based upon species and habitat abundance alone. We test the algorithm's performance and applicability on observational data of avian communities and habitat in the Peak District National Park, United Kingdom. The resulting networks correctly reveal known relationships among habitat types and known interspecific relationships. In addition, the networks produced novel insights into ecosystem structure and identified key species with high connectivity. Thus, Bayesian networks show potential for becoming a valuable tool in ecosystem analysis. PMID:20715607

  20. Artificial neural networks in NDT

    Artificial neural networks, simply known as neural networks, have attracted considerable interest in recent years largely because of a growing recognition of the potential of these computational paradigms as powerful alternative models to conventional pattern recognition or function approximation techniques. The neural networks approach is having a profound effect on almost all fields, and has been utilised in fields Where experimental inter-disciplinary work is being carried out. Being a multidisciplinary subject with a broad knowledge base, Nondestructive Testing (NDT) or Nondestructive Evaluation (NDE) is no exception. This paper explains typical applications of neural networks in NDT/NDE. Three promising types of neural networks are highlighted, namely, back-propagation, binary Hopfield and Kohonen's self-organising maps. (Author)

  1. Trends in neural network technology. Neural network gijutsu no doko

    Nishimura, K. (Toshiba Corp., Tokyo (Japan))


    The present and future of neural network technologies were reviewed. Neural networks simulate the neurons and synapses of human brain, thus permitting the utilization of heuristic knowledge difficult to describe in a logical manner. Such networks can therefore solve optimization problems, difficult to solve by conventional computers, more rapidly while sacrificing a permissible degree of rigor. In light of these advantages, many attempts have been made to apply neural networks to a variety of engineering fields including character recognition, phonetic recognition diagnosis, operation and so on. Now that these attempts have demonstrated the great potential of neural network technology, its application to practical problems will receive increasing attention. The necessity for fundamental studies on learning algorithms, modularization techniques, hardware technologies and so on will grow in conjunction with the above trends in application. 20 refs., 11 figs., 1 tab.

  2. Neural Networks in Control Applications

    Sørensen, O.

    The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all in a...... recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...

  3. Seeded Bayesian Networks: Constructing genetic networks from microarray data

    Quackenbush John


    Full Text Available Abstract Background DNA microarrays and other genomics-inspired technologies provide large datasets that often include hidden patterns of correlation between genes reflecting the complex processes that underlie cellular metabolism and physiology. The challenge in analyzing large-scale expression data has been to extract biologically meaningful inferences regarding these processes – often represented as networks – in an environment where the datasets are often imperfect and biological noise can obscure the actual signal. Although many techniques have been developed in an attempt to address these issues, to date their ability to extract meaningful and predictive network relationships has been limited. Here we describe a method that draws on prior information about gene-gene interactions to infer biologically relevant pathways from microarray data. Our approach consists of using preliminary networks derived from the literature and/or protein-protein interaction data as seeds for a Bayesian network analysis of microarray results. Results Through a bootstrap analysis of gene expression data derived from a number of leukemia studies, we demonstrate that seeded Bayesian Networks have the ability to identify high-confidence gene-gene interactions which can then be validated by comparison to other sources of pathway data. Conclusion The use of network seeds greatly improves the ability of Bayesian Network analysis to learn gene interaction networks from gene expression data. We demonstrate that the use of seeds derived from the biomedical literature or high-throughput protein-protein interaction data, or the combination, provides improvement over a standard Bayesian Network analysis, allowing networks involving dynamic processes to be deduced from the static snapshots of biological systems that represent the most common source of microarray data. Software implementing these methods has been included in the widely used TM4 microarray analysis package.

  4. Learning Local Components to Understand Large Bayesian Networks

    Zeng, Yifeng; Xiang, Yanping; Cordero, Jorge;


    (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...... 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.......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...

  5. Medical diagnosis using neural network

    Kamruzzaman, S M; Siddiquee, Abu Bakar; Mazumder, Md Ehsanul Hoque


    This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural networ...

  6. A Bayesian Networks approach to Operational Risk

    Aquaro, V.; Bardoscia, M.; Bellotti, R.; Consiglio, A.; De Carlo, F.; Ferri, G.


    A system for Operational Risk management based on the computational paradigm of Bayesian Networks is presented. The algorithm allows the construction of a Bayesian Network targeted for each bank and takes into account in a simple and realistic way the correlations among different processes of the bank. The internal losses are averaged over a variable time horizon, so that the correlations at different times are removed, while the correlations at the same time are kept: the averaged losses are thus suitable to perform the learning of the network topology and parameters; since the main aim is to understand the role of the correlations among the losses, the assessments of domain experts are not used. The algorithm has been validated on synthetic time series. It should be stressed that the proposed algorithm has been thought for the practical implementation in a mid or small sized bank, since it has a small impact on the organizational structure of a bank and requires an investment in human resources which is limited to the computational area.

  7. On local optima in learning bayesian networks

    Dalgaard, Jens; Kocka, Tomas; Pena, Jose


    This paper proposes and evaluates the k-greedy equivalence search algorithm (KES) for learning Bayesian networks (BNs) from complete data. The main characteristic of KES is that it allows a trade-off between greediness and randomness, thus exploring different good local optima. When greediness is...... set at maximum, KES corresponds to the greedy equivalence search algorithm (GES). When greediness is kept at minimum, we prove that under mild assumptions KES asymptotically returns any inclusion optimal BN with nonzero probability. Experimental results for both synthetic and real data are reported...

  8. Sensor fault diagnosis using Bayesian belief networks

    This paper describes a method based on Bayesian belief networks (BBNs) sensor fault detection, isolation, classification, and accommodation (SFDIA). For this purpose, a BBN uses three basic types of nodes to represent the information associated with each sensor: (1) sensor-reading nodes that represent the mechanisms by which the information is communicated to the BBN, (2) sensor-status nodes that convey the status of the corresponding sensors at any given time, and (3) process-variable nodes that are a conceptual representation of the actual values of the process variables, which are unknown

  9. Bayesian Network Based XP Process Modelling

    Mohamed Abouelela


    Full Text Available A Bayesian Network based mathematical model has been used for modelling Extreme Programmingsoftware development process. The model is capable of predicting the expected finish time and theexpected defect rate for each XP release. Therefore, it can be used to determine the success/failure of anyXP Project. The model takes into account the effect of three XP practices, namely: Pair Programming,Test Driven Development and Onsite Customer practices. The model’s predictions were validated againsttwo case studies. Results show the precision of our model especially in predicting the project finish time.

  10. Using imsets for learning Bayesian networks

    Vomlel, Jiří; Studený, Milan

    Praha : UTIA AV ČR, 2007 - (Kroupa, T.; Vejnarová, J.), s. 178-189 [Czech-Japan Seminar on Data Analysis and Decision Making under Uncertainty /10./. Liblice (CZ), 15.09.2007-18.09.2007] R&D Projects: GA MŠk(CZ) 1M0572 Grant ostatní: GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : Bayesian networks * artificial intelligence * probabilistic graphical models * machine learning Subject RIV: BB - Applied Statistics, Operational Research

  11. Principles of artificial neural networks

    Graupe, Daniel


    Artificial neural networks are most suitable for solving problems that are complex, ill-defined, highly nonlinear, of many and different variables, and/or stochastic. Such problems are abundant in medicine, in finance, in security and beyond. This volume covers the basic theory and architecture of the major artificial neural networks. Uniquely, it presents 18 complete case studies of applications of neural networks in various fields, ranging from cell-shape classification to micro-trading in finance and to constellation recognition - all with their respective source codes. These case studies

  12. Modular, Hierarchical Learning By Artificial Neural Networks

    Baldi, Pierre F.; Toomarian, Nikzad


    Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.

  13. Water Turbidity Modelling During Water Treatment Processes Using Artificial Neural Networks

    Rak, Adam


    Artificial neural networks are increasingly being used in the research and analysis of unit and technical processes related to water treatment. An artificial neural network model was created to predict the turbidity of treated water in a newly operating water treatment system for surface and retention water at the Sosnówka reservoir, Poland. To model water turbidity during the water treatment process for a selected system, a flexible Bayesian model of neural networks, Gaussian processes a...

  14. Some Quantum Information Inequalities from a Quantum Bayesian Networks Perspective

    Tucci, Robert R.


    This is primarily a pedagogical paper. The paper re-visits some well-known quantum information theory inequalities. It does this from a quantum Bayesian networks perspective. The paper illustrates some of the benefits of using quantum Bayesian networks to discuss quantum SIT (Shannon Information Theory).

  15. Neural Networks Of VLSI Components

    Eberhardt, Silvio P.


    Concept for design of electronic neural network calls for assembly of very-large-scale integrated (VLSI) circuits of few standard types. Each VLSI chip, which contains both analog and digital circuitry, used in modular or "building-block" fashion by interconnecting it in any of variety of ways with other chips. Feedforward neural network in typical situation operates under control of host computer and receives inputs from, and sends outputs to, other equipment.

  16. Neural Networks for Fingerprint Recognition

    Baldi, Pierre; Chauvin, Yves


    After collecting a data base of fingerprint images, we design a neural network algorithm for fingerprint recognition. When presented with a pair of fingerprint images, the algorithm outputs an estimate of the probability that the two images originate from the same finger. In one experiment, the neural network is trained using a few hundred pairs of images and its performance is subsequently tested using several thousand pairs of images originated from a subset of the database corresponding to...

  17. What are artificial neural networks?

    Krogh, Anders


    Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb......Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb...

  18. Correlational Neural Networks.

    Chandar, Sarath; Khapra, Mitesh M; Larochelle, Hugo; Ravindran, Balaraman


    Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)-based approaches and autoencoder (AE)-based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches. PMID:26654210

  19. Application of Bayesian Network Learning Methods to Land Resource Evaluation

    HUANG Jiejun; HE Xiaorong; WAN Youchuan


    Bayesian network has a powerful ability for reasoning and semantic representation, which combined with qualitative analysis and quantitative analysis, with prior knowledge and observed data, and provides an effective way to deal with prediction, classification and clustering. Firstly, this paper presented an overview of Bayesian network and its characteristics, and discussed how to learn a Bayesian network structure from given data, and then constructed a Bayesian network model for land resource evaluation with expert knowledge and the dataset. The experimental results based on the test dataset are that evaluation accuracy is 87.5%, and Kappa index is 0.826. All these prove the method is feasible and efficient, and indicate that Bayesian network is a promising approach for land resource evaluation.

  20. Neural networks: genuine artifical intelligence. Neurale netwerken: echte kunstmatige intelligentie

    Jongepier, A.G. (KEMA NV, Arnhem (Netherlands))

    Artificial neural networks are a new form of artificial intelligence. At this moment KEMA NV is examining the possibilities of applying artificial neural networks to processes that are related to power systems. A number of applications already gives hopeful results. Artificial neural networks are suited to pattern recognition. If a problem can be formulated in terms of pattern recognition, an artificial neural network may give a valuable contribution to the solution of this problem. 8 figs., 15 refs.

  1. Complex-Valued Neural Networks

    Hirose, Akira


    This book is the second enlarged and revised edition of the first successful monograph on complex-valued neural networks (CVNNs) published in 2006, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. In the second edition the recent trends in CVNNs research are included, resulting in e.g. almost a doubled number of references. The parametron invented in 1954 is also referred to with discussion on analogy and disparity. Also various additional arguments on the advantages of the complex-valued neural networks enhancing the difference to real-valued neural networks are given in various sections. The book is useful for those beginning their studies, for instance, in adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, robotics inspired by human neural systems, and brain-like information processing, as well as interdisciplina...

  2. Using consensus bayesian network to model the reactive oxygen species regulatory pathway.

    Liangdong Hu

    Full Text Available Bayesian network is one of the most successful graph models for representing the reactive oxygen species regulatory pathway. With the increasing number of microarray measurements, it is possible to construct the bayesian network from microarray data directly. Although large numbers of bayesian network learning algorithms have been developed, when applying them to learn bayesian networks from microarray data, the accuracies are low due to that the databases they used to learn bayesian networks contain too few microarray data. In this paper, we propose a consensus bayesian network which is constructed by combining bayesian networks from relevant literatures and bayesian networks learned from microarray data. It would have a higher accuracy than the bayesian networks learned from one database. In the experiment, we validated the bayesian network combination algorithm on several classic machine learning databases and used the consensus bayesian network to model the Escherichia coli's ROS pathway.

  3. Survey for Wavelet Bayesian Network Image Denoising

    Pallavi Sharma,


    Full Text Available In now days, wavelet-based image denoising method, which extends a recently emerged ―geometrical‖ Bayesian framework. The new scheme combines three criteria for distinctive theoretically useful coefficients from noise: coefficient magnitudes, their advancement across scales and spatial clustering of bulky coefficients close to image edges. These three criteria are united in a Bayesian construction. The spatial clustering properties are expressed in a earlier model. The statistical properties regarding coefficient magnitudes and their development crossways scales are expressed in a joint conditional model. We address the image denoising difficulty, where zero-mean white and homogeneous Gaussian additive noise is to be uninvolved from a given image. We employ the belief propagation (BP algorithm, which estimates a coefficient based on every one the coefficients of a picture, as the maximum-a-posterior (MAP estimator to derive the denoised wavelet coefficients. We illustrate that if the network is a spanning tree, the customary BP algorithm can achieve MAP estimation resourcefully. Our research consequences show that, in conditions of the peak-signal-to-noise-ratio and perceptual superiority, the planned approach outperforms state-of-the-art algorithms on a number of images, mostly in the textured regions, with a range of amounts of white Gaussian noise.

  4. Learning Bayesian Networks from Data by Particle Swarm Optimization


    Learning Bayesian network is an NP-hard problem. When the number of variables is large, the process of searching optimal network structure could be very time consuming and tends to return a structure which is local optimal. The particle swarm optimization (PSO) was introduced to the problem of learning Bayesian networks and a novel structure learning algorithm using PSO was proposed. To search in directed acyclic graphs spaces efficiently, a discrete PSO algorithm especially for structure learning was proposed based on the characteristics of Bayesian networks. The results of experiments show that our PSO based algorithm is fast for convergence and can obtain better structures compared with genetic algorithm based algorithms.

  5. COCOMO Estimates Using Neural Networks

    Anupama Kaushik


    Full Text Available Software cost estimation is an important phase in software development. It predicts the amount of effort and development time required to build a software system. It is one of the most critical tasks and an accurate estimate provides a strong base to the development procedure. In this paper, the most widely used software cost estimation model, the Constructive Cost Model (COCOMO is discussed. The model is implemented with the help of artificial neural networks and trained using the perceptron learning algorithm. The COCOMO dataset is used to train and to test the network. The test results from the trained neural network are compared with that of the COCOMO model. The aim of our research is to enhance the estimation accuracy of the COCOMO model by introducing the artificial neural networks to it.

  6. Neural Networks and Database Systems

    Schikuta, Erich


    Object-oriented database systems proved very valuable at handling and administrating complex objects. In the following guidelines for embedding neural networks into such systems are presented. It is our goal to treat networks as normal data in the database system. From the logical point of view, a neural network is a complex data value and can be stored as a normal data object. It is generally accepted that rule-based reasoning will play an important role in future database applications. The knowledge base consists of facts and rules, which are both stored and handled by the underlying database system. Neural networks can be seen as representation of intensional knowledge of intelligent database systems. So they are part of a rule based knowledge pool and can be used like conventional rules. The user has a unified view about his knowledge base regardless of the origin of the unique rules.

  7. Logistic regression against a divergent Bayesian network

    Noel Antonio Sánchez Trujillo


    Full Text Available This article is a discussion about two statistical tools used for prediction and causality assessment: logistic regression and Bayesian networks. Using data of a simulated example from a study assessing factors that might predict pulmonary emphysema (where fingertip pigmentation and smoking are considered; we posed the following questions. Is pigmentation a confounding, causal or predictive factor? Is there perhaps another factor, like smoking, that confounds? Is there a synergy between pigmentation and smoking? The results, in terms of prediction, are similar with the two techniques; regarding causation, differences arise. We conclude that, in decision-making, the sum of both: a statistical tool, used with common sense, and previous evidence, taking years or even centuries to develop; is better than the automatic and exclusive use of statistical resources.

  8. Learning Bayesian network structure with immune algorithm

    Zhiqiang Cai; Shubin Si; Shudong Sun; Hongyan Dui


    Finding out reasonable structures from bulky data is one of the difficulties in modeling of Bayesian network (BN), which is also necessary in promoting the application of BN. This pa-per proposes an immune algorithm based method (BN-IA) for the learning of the BN structure with the idea of vaccination. Further-more, the methods on how to extract the effective vaccines from local optimal structure and root nodes are also described in details. Final y, the simulation studies are implemented with the helicopter convertor BN model and the car start BN model. The comparison results show that the proposed vaccines and the BN-IA can learn the BN structure effectively and efficiently.

  9. Bayesian network learning with cutting planes

    Cussens, James


    The problem of learning the structure of Bayesian networks from complete discrete data with a limit on parent set size is considered. Learning is cast explicitly as an optimisation problem where the goal is to find a BN structure which maximises log marginal likelihood (BDe score). Integer programming, specifically the SCIP framework, is used to solve this optimisation problem. Acyclicity constraints are added to the integer program (IP) during solving in the form of cutting planes. Finding good cutting planes is the key to the success of the approach -the search for such cutting planes is effected using a sub-IP. Results show that this is a particularly fast method for exact BN learning.

  10. Inference of Gene Regulatory Network Based on Local Bayesian Networks

    Liu, Fei; Zhang, Shao-Wu; Guo, Wei-Feng; Chen, Luonan


    The inference of gene regulatory networks (GRNs) from expression data can mine the direct regulations among genes and gain deep insights into biological processes at a network level. During past decades, numerous computational approaches have been introduced for inferring the GRNs. However, many of them still suffer from various problems, e.g., Bayesian network (BN) methods cannot handle large-scale networks due to their high computational complexity, while information theory-based methods cannot identify the directions of regulatory interactions and also suffer from false positive/negative problems. To overcome the limitations, in this work we present a novel algorithm, namely local Bayesian network (LBN), to infer GRNs from gene expression data by using the network decomposition strategy and false-positive edge elimination scheme. Specifically, LBN algorithm first uses conditional mutual information (CMI) to construct an initial network or GRN, which is decomposed into a number of local networks or GRNs. Then, BN method is employed to generate a series of local BNs by selecting the k-nearest neighbors of each gene as its candidate regulatory genes, which significantly reduces the exponential search space from all possible GRN structures. Integrating these local BNs forms a tentative network or GRN by performing CMI, which reduces redundant regulations in the GRN and thus alleviates the false positive problem. The final network or GRN can be obtained by iteratively performing CMI and local BN on the tentative network. In the iterative process, the false or redundant regulations are gradually removed. When tested on the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in E.coli, our results suggest that LBN outperforms other state-of-the-art methods (ARACNE, GENIE3 and NARROMI) significantly, with more accurate and robust performance. In particular, the decomposition strategy with local Bayesian networks not only effectively reduce

  11. Inference of Gene Regulatory Network Based on Local Bayesian Networks.

    Liu, Fei; Zhang, Shao-Wu; Guo, Wei-Feng; Wei, Ze-Gang; Chen, Luonan


    The inference of gene regulatory networks (GRNs) from expression data can mine the direct regulations among genes and gain deep insights into biological processes at a network level. During past decades, numerous computational approaches have been introduced for inferring the GRNs. However, many of them still suffer from various problems, e.g., Bayesian network (BN) methods cannot handle large-scale networks due to their high computational complexity, while information theory-based methods cannot identify the directions of regulatory interactions and also suffer from false positive/negative problems. To overcome the limitations, in this work we present a novel algorithm, namely local Bayesian network (LBN), to infer GRNs from gene expression data by using the network decomposition strategy and false-positive edge elimination scheme. Specifically, LBN algorithm first uses conditional mutual information (CMI) to construct an initial network or GRN, which is decomposed into a number of local networks or GRNs. Then, BN method is employed to generate a series of local BNs by selecting the k-nearest neighbors of each gene as its candidate regulatory genes, which significantly reduces the exponential search space from all possible GRN structures. Integrating these local BNs forms a tentative network or GRN by performing CMI, which reduces redundant regulations in the GRN and thus alleviates the false positive problem. The final network or GRN can be obtained by iteratively performing CMI and local BN on the tentative network. In the iterative process, the false or redundant regulations are gradually removed. When tested on the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in E.coli, our results suggest that LBN outperforms other state-of-the-art methods (ARACNE, GENIE3 and NARROMI) significantly, with more accurate and robust performance. In particular, the decomposition strategy with local Bayesian networks not only effectively reduce

  12. A Flexible Software System for Learning Bayesian Networks from data

    Aabakken, Trond


    Bayesian networks, also referred to as belief networks, originates from the artificial intelligence field where they were used to reason about uncertain knowledge. They differ from other knowledge representation schemes as they constitute a model of the environment rather than a model of the reasoning process. Among the Bayesian networks' main assets is that they offer a sound methodology for combining (a priori) information a domain expert may have with information available in databases. I...

  13. Automatic Generation of Neural Networks

    A. Fiszelew; P. Britos; G. Perichisky; R. García-Martínez


    This work deals with methods for finding optimal neural network architectures to learn particular problems. A genetic algorithm is used to discover suitable domain specific architectures; this evolutionary algorithm applies direct codification and uses the error from the trained network as a performance measure to guide the evolution. The network training is accomplished by the back-propagation algorithm; techniques such as training repetition, early stopping and complex regulation are employ...

  14. Approximation methods for efficient learning of Bayesian networks

    Riggelsen, C


    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.

  15. Video Compression Using Neural Network

    Sangeeta Mishra


    Full Text Available Apart from the existing technology on image compression represented by series of JPEG, MPEG and H.26x standards, new technology such as neural networks and genetic algorithms are being developed to explore the future of image coding. Successful applications of neural networks to basic propagation algorithm have now become well established and other aspects of neural network involvement in this technology. In this paper different algorithms were implemented like gradient descent back propagation, gradient descent with momentum back propagation, gradient descent with adaptive learning back propagation, gradient descent with momentum and adaptive learning back propagation and Levenberg-Marquardt algorithm. The size of original video clip is 25MB and after compression it becomes 21.3MB giving the compression ratio as 85.2% and compression factor of 1.174. It was observed that the size remains same after compression but the difference is in the clarity.

  16. Neural networks in signal processing

    Nuclear Engineering has matured during the last decade. In research and design, control, supervision, maintenance and production, mathematical models and theories are used extensively. In all such applications signal processing is embedded in the process. Artificial Neural Networks (ANN), because of their nonlinear, adaptive nature are well suited to such applications where the classical assumptions of linearity and second order Gaussian noise statistics cannot be made. ANN's can be treated as nonparametric techniques, which can model an underlying process from example data. They can also adopt their model parameters to statistical change with time. Algorithms in the framework of Neural Networks in Signal processing have found new applications potentials in the field of Nuclear Engineering. This paper reviews the fundamentals of Neural Networks in signal processing and their applications in tasks such as recognition/identification and control. The topics covered include dynamic modeling, model based ANN's, statistical learning, eigen structure based processing and generalization structures. (orig.)


    Santosh Kumar Chaudhari


    Full Text Available A Network Management System (NMS plays a very important role in managing an ever-evolving telecommunication network. Generally an NMS monitors & maintains the health of network elements. The growing size of the network warrants extra functionalities from the NMS. An NMS provides all kinds of information about networks which can be used for other purposes apart from monitoring & maintaining networks like improving QoS & saving energy in the network. In this paper, we add another dimension to NMS services, namely, making an NMS energy aware. We propose a Decision Management System (DMS framework which uses a machine learning technique called Bayesian Belief Networks (BBN, to make the NMS energy aware. The DMS is capable of analysing and making control decisions based on network traffic. We factor in the cost of rerouting and power saving per port. Simulations are performed on standard network topologies, namely, ARPANet and IndiaNet. It is found that ~2.5-6.5% power can be saved.

  18. Relations Between Wavelet Network and Feedforward Neural Network

    刘志刚; 何正友; 钱清泉


    A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation functions in wavelet network by different activation functions in feedforward neural network. It is concluded that some wavelet function is equal to the linear combination of several neurons in feedforward neural network.

  19. Automatic classification of eclipsing binaries light curves using neural networks

    Sarro, L M; Giménez, A


    In this work we present a system for the automatic classification of the light curves of eclipsing binaries. This system is based on a classification scheme that aims to separate eclipsing binary sistems according to their geometrical configuration in a modified version of the traditional classification scheme. The classification is performed by a Bayesian ensemble of neural networks trained with {\\em Hipparcos} data of seven different categories including eccentric binary systems and two types of pulsating light curve morphologies.

  20. Application of neural networks in coastal engineering

    Mandal, S.

    the neural network attractive. A neural network is an information processing system modeled on the structure of the dynamic process. It can solve the complex/nonlinear problems quickly once trained by operating on problems using an interconnected number...

  1. Plant Growth Models Using Artificial Neural Networks

    Bubenheim, David


    In this paper, we descrive our motivation and approach to devloping models and the neural network architecture. Initial use of the artificial neural network for modeling the single plant process of transpiration is presented.

  2. Ocean wave forecasting using recurrent neural networks

    Mandal, S.; Prabaharan, N.

    , merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper describes an artificial neural network, namely recurrent neural network with rprop update algorithm and is applied for wave forecasting. Measured ocean waves off...

  3. Neural network exploitation in reliability assurance

    The contribution deals with neural network application for the diagnostic system of the three-phase asynchronous electro motor. The case study is done and can be used as a model for the next application of neural network methodology.

  4. Developing Large-Scale Bayesian Networks by Composition

    National Aeronautics and Space Administration — In this paper, we investigate the use of Bayesian networks to construct large-scale diagnostic systems. In particular, we consider the development of large-scale...

  5. Macroscopic Models of Clique Tree Growth for Bayesian Networks

    National Aeronautics and Space Administration — In clique tree clustering, inference consists of propagation in a clique tree compiled from a Bayesian network. In this paper, we develop an analytical approach to...

  6. Designing Resource-Bounded Reasoners using Bayesian Networks

    National Aeronautics and Space Administration — In this work we are concerned with the conceptual design of large-scale diagnostic and health management systems that use Bayesian networks. While they are...

  7. Neural Networks for Flight Control

    Jorgensen, Charles C.


    Neural networks are being developed at NASA Ames Research Center to permit real-time adaptive control of time varying nonlinear systems, enhance the fault-tolerance of mission hardware, and permit online system reconfiguration. In general, the problem of controlling time varying nonlinear systems with unknown structures has not been solved. Adaptive neural control techniques show considerable promise and are being applied to technical challenges including automated docking of spacecraft, dynamic balancing of the space station centrifuge, online reconfiguration of damaged aircraft, and reducing cost of new air and spacecraft designs. Our experiences have shown that neural network algorithms solved certain problems that conventional control methods have been unable to effectively address. These include damage mitigation in nonlinear reconfiguration flight control, early performance estimation of new aircraft designs, compensation for damaged planetary mission hardware by using redundant manipulator capability, and space sensor platform stabilization. This presentation explored these developments in the context of neural network control theory. The discussion began with an overview of why neural control has proven attractive for NASA application domains. The more important issues in control system development were then discussed with references to significant technical advances in the literature. Examples of how these methods have been applied were given, followed by projections of emerging application needs and directions.

  8. Bayesian Network Structure Learning from Limited Datasets through Graph Evolution

    Tonda, Alberto; Lutton, Evelyne; Reuillon, Romain; Squillero, Giovanni; Wuillemin, Pierre-Henri


    Bayesian networks are stochastic models, widely adopted to encode knowledge in several fields. One of the most interesting features of a Bayesian network is the possibility of learning its structure from a set of data, and subsequently use the resulting model to perform new predictions. Structure learning for such models is a NP-hard problem, for which the scientific community developed two main approaches: score-and-search metaheuristics, often evolutionary-based, and dependency-analysis det...

  9. On polyhedral approximations of polytopes for learning Bayesian networks

    Studený, Milan; Haws, D.C.


    Roč. 4, č. 1 (2013), s. 59-92. ISSN 1309-3452 R&D Projects: GA ČR GA201/08/0539 Institutional support: RVO:67985556 Keywords : Bayesian network structure * integer programming * standard imset * characteristic imset * LP relaxation Subject RIV: BA - General Mathematics polyhedral approximations of polytopes for learning bayesian networks.pdf

  10. Uncertainty management using bayesian networks in student knowledge diagnosis

    Adina COCU; Diana STEFANESCU


    In intelligent tutoring systems, student or user modeling implies dealing with imperfect and uncertain knowledge. One of the artificial intelligence techniques used for uncertainty management is that of Bayesian networks. This paradigm is recommended in the situation when exist dependencies between data and qualitative information about these data. In this work we present a student knowledge diagnosis model based on representation with Bayesian networks. The educational system incorporate a m...

  11. Strategies for Generating Micro Explanations for Bayesian Belief Networks

    Sember, Peter; Zukerman, Ingrid


    Bayesian Belief Networks have been largely overlooked by Expert Systems practitioners on the grounds that they do not correspond to the human inference mechanism. In this paper, we introduce an explanation mechanism designed to generate intuitive yet probabilistically sound explanations of inferences drawn by a Bayesian Belief Network. In particular, our mechanism accounts for the results obtained due to changes in the causal and the evidential support of a node.

  12. Risk Based Maintenance of Offshore Wind Turbines Using Bayesian Networks

    Nielsen, Jannie Jessen; Sørensen, John Dalsgaard


    This paper presents how Bayesian networks can be used to make optimal decisions for repairs of offshore wind turbines. The Bayesian network is an efficient tool for updating a deterioration model whenever new information becomes available from inspections/monitoring. The optimal decision is found such that the preventive maintenance effort is balanced against the costs to corrective maintenance including indirect costs to reduced production. The basis for the optimization is the risk based Ba...

  13. Building a Chaotic Proved Neural Network

    Bahi, Jacques M; Salomon, Michel


    Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.

  14. Neural Network Adaptations to Hardware Implementations

    Moerland, Perry,; Fiesler,Emile


    In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential.However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and ...

  15. Neural Network Adaptations to Hardware Implementations

    Moerland, Perry,; Fiesler,Emile; Beale, R


    In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential. However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and...

  16. Neural networks and applications tutorial

    Guyon, I.


    The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

  17. Deep Gate Recurrent Neural Network

    Gao, Yuan; Glowacka, Dorota


    This paper introduces two recurrent neural network structures called Simple Gated Unit (SGU) and Deep Simple Gated Unit (DSGU), which are general structures for learning long term dependencies. Compared to traditional Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), both structures require fewer parameters and less computation time in sequence classification tasks. Unlike GRU and LSTM, which require more than one gates to control information flow in the network, SGU and DSGU only...

  18. Network Firewall using Artificial Neural Networks

    Kristián Valentín; Michal Malý


    Today's most common firewalls are mostly rule-based. Their knowledge consists of a set of rules upon which they process received packets. They cannot do anything they have not been explicitly configured to do. This makes the system more straightforward to set up, but less flexible and less adaptive to changing circumstances. We will investigate a network firewall whose rule-base we will try to model using an artificial neural network, more specifically using a multi-layer perceptron (MLP) tra...

  19. Artificial neural networks in medicine

    Keller, P.E.


    This Technology Brief provides an overview of artificial neural networks (ANN). A definition and explanation of an ANN is given and situations in which an ANN is used are described. ANN applications to medicine specifically are then explored and the areas in which it is currently being used are discussed. Included are medical diagnostic aides, biochemical analysis, medical image analysis and drug development.

  20. Medical Imaging with Neural Networks

    The objective of this paper is to provide an overview of the recent developments in the use of artificial neural networks in medical imaging. The areas of medical imaging that are covered include : ultrasound, magnetic resonance, nuclear medicine and radiological (including computerized tomography). (authors)

  1. Aphasia Classification Using Neural Networks

    Axer, H.; Jantzen, Jan; Berks, G.;


    A web-based software model ( was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests of the...

  2. Model Of Neural Network With Creative Dynamics

    Zak, Michail; Barhen, Jacob


    Paper presents analysis of mathematical model of one-neuron/one-synapse neural network featuring coupled activation and learning dynamics and parametrical periodic excitation. Demonstrates self-programming, partly random behavior of suitable designed neural network; believed to be related to spontaneity and creativity of biological neural networks.

  3. Simplified LQG Control with Neural Networks

    Sørensen, O.


    A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce a...

  4. Using Bayesian Networks to Improve Knowledge Assessment

    Millan, Eva; Descalco, Luis; Castillo, Gladys; Oliveira, Paula; Diogo, Sandra


    In this paper, we describe the integration and evaluation of an existing generic Bayesian student model (GBSM) into an existing computerized testing system within the Mathematics Education Project (PmatE--Projecto Matematica Ensino) of the University of Aveiro. This generic Bayesian student model had been previously evaluated with simulated…

  5. Study of Online Bayesian Networks Learning in a Multi-Agent System

    Yonghui Cao


    Full Text Available This paper introduces online Bayesian network learning in detail. The structural and parametric learning abilities of the online Bayesian network learning are explored. The paper starts with revisiting the multi-agent self-organization problem and the proposed solution. Then, we explain the proposed Bayesian network learning, three scoring functions, namely Log-Likelihood, Minimum description length, and Bayesian scores.

  6. Study of Online Bayesian Networks Learning in a Multi-Agent System

    Yonghui Cao


    This paper introduces online Bayesian network learning in detail. The structural and parametric learning abilities of the online Bayesian network learning are explored. The paper starts with revisiting the multi-agent self-organization problem and the proposed solution. Then, we explain the proposed Bayesian network learning, three scoring functions, namely Log-Likelihood, Minimum description length, and Bayesian scores.

  7. A Bayesian Networks in Intrusion Detection Systems

    M. Mehdi


    Full Text Available Intrusion detection systems (IDSs have been widely used to overcome security threats in computer networks. Anomaly-based approaches have the advantage of being able to detect previously unknown attacks, but they suffer from the difficulty of building robust models of acceptable behaviour which may result in a large number of false alarms caused by incorrect classification of events in current systems. We propose a new approach of an anomaly Intrusion detection system (IDS. It consists of building a reference behaviour model and the use of a Bayesian classification procedure associated to unsupervised learning algorithm to evaluate the deviation between current and reference behaviour. Continuous re-estimation of model parameters allows for real time operation. The use of recursive Log-likelihood and entropy estimation as a measure for monitoring model degradation related with behavior changes and the associated model update show that the accuracy of the event classification process is significantly improved using our proposed approach for reducing the missing-alarm.


    Mariana D.C. Lima


    Full Text Available Bayesian Network (BN is a classification technique widely used in Artificial Intelligence. Its structure is a Direct Acyclic Graph (DAG used to model the association of categorical variables. However, in cases where the variables are numerical, a previous discretization is necessary. Discretization methods are usually based on a statistical approach using the data distribution, such as division by quartiles. In this article we present a discretization using a heuristic that identifies events called peak and valley. Genetic Algorithm was used to identify these events having the minimization of the error between the estimated average for BN and the actual value of the numeric variable output as the objective function. The BN has been modeled from a database of Bit’s Rate of Penetration of the Brazilian pre-salt layer with 5 numerical variables and one categorical variable, using the proposed discretization and the division of the data by the quartiles. The results show that the proposed heuristic discretization has higher accuracy than the quartiles discretization.

  9. Fuzzy Neural Networks for water level and discharge forecasting

    Alvisi, Stefano; Franchini, Marco


    A new procedure for water level (or discharge) forecasting under uncertainty using artificial neural networks is proposed: uncertainty is expressed in the form of a fuzzy number. For this purpose, the parameters of the neural network, namely, the weights and biases, are represented by fuzzy numbers rather than crisp numbers. Through the application of the extension principle, the fuzzy number representative of the output variable (water level or discharge) is then calculated at each time step on the basis of a set of crisp inputs and fuzzy parameters of the neural network. The proposed neural network thus allows uncertainty to be taken into account at the forecasting stage not providing only deterministic or crisp predictions, but rather predictions in terms of 'the discharge (or level) will fall between two values, indicated according to the level of credibility considered, whereas it will take on a certain value when the level of credibility is maximum'. The fuzzy parameters of the neural network are estimated using a calibration procedure that imposes a constraint whereby for an assigned h-level the envelope of the corresponding intervals representing the outputs (forecasted levels or discharges, calculated at different points in time) must include a prefixed percentage of observed values. The proposed model is applied to two different case studies. Specifically, the data related to the first case study are used to develop and test a flood event-based water level forecasting model, whereas the data related to the latter are used for continuous discharge forecasting. The results obtained are compared with those provided by other data-driven models - Bayesian neural networks (Neal, R.M. 1992, Bayesian training of backpropagation networks by the hybrid Monte Carlo method. Tech. Rep. CRG-TR-92-1, Dep. of Comput. Sci., Univ. of Toronto, Toronto, Ont., Canada.) and the Local Uncertainty Estimation Model (Shrestha D.L. and Solomatine D.P. 2006, Machine learning


    Vikas Kumar


    Full Text Available This paper comparator networks - a well-known modelof parallel computation. This model is used extensivelyfor keys arrangement tasks such as sorting and selection.This work investigates several aspects of comparatornetworks. It starts with presenting handy tools foranalysis of comparator networks in the form ofconclusive sets - non-binary vectors that verify a specificfunctionality. The 0-1 principle introduced by Knuthstates that a comparator network is a sorting network ifand only if it sorts all binary inputs. Hence, it points out acertain binary conclusive set. We compare these twomodels by considering several 0-1 -like principles andshow that the min-max model is the ‘strongest’ model ofcomputation which obeys our principles. That is, if afunction is computable in a model of computation inwhich any of these principles holds, a min-max networkcan compute this function.

  11. Probabilistic neural networks for infrared imaging target discrimination

    Cayouette, Patrice; Labonte, G.; Morin, A.


    The next generation of infrared imaging trackers and seekers will allow for the implementation of more smarter tracking algorithms, able to keep a positive lock on a targeted aircraft in the presence of countermeasures. Pattern recognition algorithms will be able to select targets based on features extracted from all possible targets images. Artificial neural networks provide an important class of such algorithms. In particular, probabilistic neural networks perform almost as optimal Bayesian classifiers, by approximating the probability density functions of the features of the objects. Furthermore, these neural networks generate an output that indicates the confidence it has in its answer. We have evaluated the the possibility of integrating such neural networks in an infrared imaging seeker emulator, devised by the Defense Research and Development establishment at Valcartier. We describe the characteristics extracted from the images and define translation invariant features from these. We give a basis for the selection of which features to use as input for the neural network. We build the network and test it on some real data. Results are shown, which indicate a remarkable efficiency of over 98% correct recognition. For most of the images on which the neural network makes its mistakes, even a human expert would probably have been mistaken. We build a reduced version of this network, with 82% fewer neurons, and only a 0.6% less precision. Such a neural network could well be used in a real time system because its computing time on a normal PC gives a rate of over 5,300 patterns per second.

  12. Dynamic properties of cellular neural networks

    Angela Slavova


    Full Text Available Dynamic behavior of a new class of information-processing systems called Cellular Neural Networks is investigated. In this paper we introduce a small parameter in the state equation of a cellular neural network and we seek for periodic phenomena. New approach is used for proving stability of a cellular neural network by constructing Lyapunov's majorizing equations. This algorithm is helpful for finding a map from initial continuous state space of a cellular neural network into discrete output. A comparison between cellular neural networks and cellular automata is made.

  13. Photon spectrometry utilizing neural networks

    Having in mind the time spent on the uneventful work of characterization of the radiation beams used in a ionizing radiation metrology laboratory, the Metrology Service of the Centro Regional de Ciencias Nucleares do Nordeste - CRCN-NE verified the applicability of artificial intelligence (artificial neural networks) to perform the spectrometry in photon fields. For this, was developed a multilayer neural network, as an application for the classification of patterns in energy, associated with a thermoluminescent dosimetric system (TLD-700 and TLD-600). A set of dosimeters was initially exposed to various well known medium energies, between 40 keV and 1.2 MeV, coinciding with the beams determined by ISO 4037 standard, for the dose of 10 mSv in the quantity Hp(10), on a chest phantom (ISO slab phantom) with the purpose of generating a set of training data for the neural network. Subsequently, a new set of dosimeters irradiated in unknown energies was presented to the network with the purpose to test the method. The methodology used in this work was suitable for application in the classification of energy beams, having obtained 100% of the classification performed. (authors)

  14. Fuzzy logic systems are equivalent to feedforward neural networks


    Fuzzy logic systems and feedforward neural networks are equivalent in essence. First, interpolation representations of fuzzy logic systems are introduced and several important conclusions are given. Then three important kinds of neural networks are defined, i.e. linear neural networks, rectangle wave neural networks and nonlinear neural networks. Then it is proved that nonlinear neural networks can be represented by rectangle wave neural networks. Based on the results mentioned above, the equivalence between fuzzy logic systems and feedforward neural networks is proved, which will be very useful for theoretical research or applications on fuzzy logic systems or neural networks by means of combining fuzzy logic systems with neural networks.

  15. Spiking Neural P Systems and Modularization of Complex Networks from Cortical Neural Network to Social Networks

    Obtulowicz, Adam


    An idea of modularization of complex networks (from cortial neural net, Internet computer network, to market and social networks) is explained and some its topic motivations are presented. Then some known modularization algorithms and modular architectures (constructions) of complex networks are discussed in the context of possible applications of spiking neural P systems in order to improve these modularization algorithms and to analyze massively parallel processes in networks of mo...

  16. Neural Networks Methodology and Applications

    Dreyfus, Gérard


    Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts ands seemlessly edited to present a coherent and comprehensive, yet not redundant, practically-oriented...


    Nada M. Al Sallami


    Full Text Available This paper discusses a proposed load balance technique based on artificial neural network. It distributes workload equally across all the nodes by using back propagation learning algorithm to train feed forward Artificial Neural Network (ANN. The proposed technique is simple and it can work efficiently when effective training sets are used. ANN predicts the demand and thus allocates resources according to that demand. Thus, it always maintains the active servers according to current demand, which results in low energy consumption than the conservative approach of over-provisioning. Furthermore, high utilization of server results in more power consumption, server running at higher utilization can process more workload with similar power usage. Finally the existing load balancing techniques in cloud computing are discussed and compared with the proposed technique based on various parameters like performance, scalability, associated overhead... etc. In addition energy consumption and carbon emission perspective are also considered to satisfy green computing.

  18. Color conversion using neural networks

    Tominaga, Shoji


    Neural network methods are described for color coordinate conversion between color systems. We present solutions for two problems of (1) conversion between two color-specification systems and (2) conversion between a color-specification system and a device coordinate system. First we discuss the color-notation conversion between the Munsell and CIE color systems. The conversion algorithms are developed for both directions of Munsell-to-L*a*b* and L*a*b*-to-Munsell. Second we discuss a neural network method for color reproduction on a printer. The color reproduction problem on the printer using more than four inks is considered as the problem of controlling an unknown system. The practical algorithms are presented for realizing the mapping from the L*a*b* space to the CMYK space. Moreover the method is applied to the color control using CMYK plus light cyan and light magenta.

  19. International joint conference on neural networks


    This book contains papers on neural networks. Included are the following topics: A self-training visual inspection system with a neural network classifier; A bifurcation theory approach to vector field programming for periodic attractors; and construction of neural nets using the radon transform.

  20. A Decomposition Algorithm for Learning Bayesian Network Structures from Data

    Zeng, Yifeng; Cordero Hernandez, Jorge


    the complete network. The new learning algorithm firstly finds local components from the data, and then recover the complete network by joining the learned components. We show the empirical performance of the decomposition algorithm in several benchmark networks.......It is a challenging task of learning a large Bayesian network from a small data set. Most conventional structural learning approaches run into the computational as well as the statistical problems. We propose a decomposition algorithm for the structure construction without having to learn...

  1. Learning Compact Recurrent Neural Networks

    Lu, Zhiyun; Sindhwani, Vikas; Sainath, Tara N.


    Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via low-rank factorizations and parameter sharing schemes. Our goal is to investigate redundancies in recurrent architectures where compression ca...

  2. Learning with heterogeneous neural networks

    Belanche Muñoz, Luis Antonio


    This chapter studies a class of neuron models that computes a user-defined similarity function between inputs and weights. The neuron transfer function is formed by composition of an adapted logistic function with the quasi-linear mean of the partial input-weight similarities. The neuron model is capable of dealing directly with mixtures of continuous as well as discrete quantities, among other data types and there is provision for missing values. An artificial neural network using these n...

  3. Flood quantile estimation at ungauged sites by Bayesian networks

    Mediero, L.; Santillán, D.; Garrote, L.


    Estimating flood quantiles at a site for which no observed measurements are available is essential for water resources planning and management. Ungauged sites have no observations about the magnitude of floods, but some site and basin characteristics are known. The most common technique used is the multiple regression analysis, which relates physical and climatic basin characteristic to flood quantiles. Regression equations are fitted from flood frequency data and basin characteristics at gauged sites. Regression equations are a rigid technique that assumes linear relationships between variables and cannot take the measurement errors into account. In addition, the prediction intervals are estimated in a very simplistic way from the variance of the residuals in the estimated model. Bayesian networks are a probabilistic computational structure taken from the field of Artificial Intelligence, which have been widely and successfully applied to many scientific fields like medicine and informatics, but application to the field of hydrology is recent. Bayesian networks infer the joint probability distribution of several related variables from observations through nodes, which represent random variables, and links, which represent causal dependencies between them. A Bayesian network is more flexible than regression equations, as they capture non-linear relationships between variables. In addition, the probabilistic nature of Bayesian networks allows taking the different sources of estimation uncertainty into account, as they give a probability distribution as result. A homogeneous region in the Tagus Basin was selected as case study. A regression equation was fitted taking the basin area, the annual maximum 24-hour rainfall for a given recurrence interval and the mean height as explanatory variables. Flood quantiles at ungauged sites were estimated by Bayesian networks. Bayesian networks need to be learnt from a huge enough data set. As observational data are reduced, a

  4. Process Neural Networks Theory and Applications

    He, Xingui


    "Process Neural Networks - Theory and Applications" proposes the concept and model of a process neural network for the first time, showing how it expands the mapping relationship between the input and output of traditional neural networks, and enhancing the expression capability for practical problems, with broad applicability to solving problems relating to process in practice. Some theoretical problems such as continuity, functional approximation capability, and computing capability, are strictly proved. The application methods, network construction principles, and optimization alg

  5. using artificial neural network

    Rafael do Espírito Santo


    Full Text Available In this work, a Multilayer Perceptron implementation – MLP using functional Magnetic Resonance Imaging (fMRI is used to infer stimuli performed. Sets of images of brain activation were generated by visual, auditory and finger tapping paradigms in 54 healthy volunteers. These images were used for training the MLP network in a leave-one-out manner in order to predict the paradigm that a subject performed by using other images, so far unseen by the MLP network. The aim in this paper is the exploring of the influence of the number of the Principal Component (PC on the performance of the MLP in classifying fMRI paradigms. The classifier´s performance was evaluated in terms of the Sensitivity and Specificity, Prediction Accuracy and the area Az under the receiver operating characteristics (ROC curve. From the ROC analysis, values of Az up to 1 were obtained with 60 PCs in discriminating the visual paradigm from the auditory paradigm.

  6. Bayesian networks for mastitis management on dairy farms

    Steeneveld, Wilma; van der Gaag, Linda; Barkema, H.W.; Hogeveen, H.


    This manuscript presents the idea of providing dairy farmers with probability distributions to support decisions on mastitis management and illustrates its feasibility by two applications. Naive Bayesian networks were developed for both applications. The networks in the first application were used t

  7. The LILARTI neural network system

    Allen, J.D. Jr.; Schell, F.M.; Dodd, C.V.


    The material of this Technical Memorandum is intended to provide the reader with conceptual and technical background information on the LILARTI neural network system of detail sufficient to confer an understanding of the LILARTI method as it is presently allied and to facilitate application of the method to problems beyond the scope of this document. Of particular importance in this regard are the descriptive sections and the Appendices which include operating instructions, partial listings of program output and data files, and network construction information.

  8. Practical neural network recipies in C++



    This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assum


    Artur Popko


    Full Text Available Recognition of visual patterns is one of significant applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In the paper, a simplified neural approach to recognition of visual patterns is portrayed and discussed. This paper is dedicated for investigators in visual patterns recognition, Artificial Neural Networking and related disciplines. The document describes also MemBrain application environment as a powerful and easy to use neural networks’ editor and simulator supporting ANN.

  10. Accurate Forecasting Prediction of Foreign Exchange Rate Using Neural Network Algorithms: A STUDY

    Divyapriya .R


    Full Text Available Data mining is a form of knowledge discovery essential for solving problems in a specific domain.Classification is a technique used for discovering classes of unknown data. Several major kinds ofclassification method including decision tree induction, Bayesian networks, k-nearest neighbour classifier,case-based reasoning, genetic algorithm, fuzzy logic techniques and neural networks etc. A neural network isa massively parallel distributed processor that has a natural propensity for storing experimental knowledgeand making it available for use. Artificial Neural Networks [ANN] are nonlinear information processingdevices which are built from interconnected elementary processing devices called neurons. The goal of thisstudy is to find the efficiency of the existing artificial neural network algorithm on forecasting foreignexchange rate. Back propagation Algorithm, Hidden Markov Model, recurrent neural networks are thealgorithms selected for the study. The back propagation algorithm gives finite accuracy in foreign exchangerate.

  11. Fuzzy ARTMAP neural network for seafloor classification from multibeam sonar data

    Zhou Xinghua; Chen Yongqi; Nick Emerson; Du Dewen


    This paper presents a seafloor classification method of multibeam sonar data, based on the use of Adaptive Resonance Theory (ART) neural networks. A general ART-based neural network, Fuzzy ARTMAP, has been proposed for seafloor classification of multibeam sonar data. An evolutionary strategy was used to generate new training samples near the cluster boundaries of the neural network, therefore the weights can be revised and refined by supervised learning. The proposed method resolves the training problem for Fuzzy ARTMAP neural networks, which are applied to seafloor classification of multibeam sonar data when there are less than adequate ground-truth samples. The results were synthetically analyzed in comparison with the standard Fuzzy ARTMAP network and a conventional Bayesian classifier.The conclusion can be drawn that Fuzzy ARTMAP neural networks combining with GA algorithms can be alternative powerful tools for seafloor classification of multibeam sonar data.

  12. Neural network modeling of emotion

    Levine, Daniel S.


    This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.

  13. Neural-Network Computer Transforms Coordinates

    Josin, Gary M.


    Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.

  14. Dynamic Analysis of Structures Using Neural Networks

    N. Ahmadi


    Full Text Available In the recent years, neural networks are considered as the best candidate for fast approximation with arbitrary accuracy in the time consuming problems. Dynamic analysis of structures against earthquake has the time consuming process. We employed two kinds of neural networks: Generalized Regression neural network (GR and Back-Propagation Wavenet neural network (BPW, for approximating of dynamic time history response of frame structures. GR is a traditional radial basis function neural network while BPW categorized as a wavelet neural network. In BPW, sigmoid activation functions of hidden layer neurons are substituted with wavelets and weights training are achieved using Scaled Conjugate Gradient (SCG algorithm. Comparison the results of BPW with those of GR in the dynamic analysis of eight story steel frame indicates that accuracy of the properly trained BPW was better than that of GR and therefore, BPW can be efficiently used for approximate dynamic analysis of structures.

  15. Uncertainty Modeling Based on Bayesian Network in Ontology Mapping

    LI Yuhua; LIU Tao; SUN Xiaolin


    How to deal with uncertainty is crucial in exact concept mapping between ontologies. This paper presents a new framework on modeling uncertainty in ontologies based on bayesian networks (BN). In our approach, ontology Web language (OWL) is extended to add probabilistic markups for attaching probability information, the source and target ontologies (expressed by patulous OWL) are translated into bayesian networks (BNs), the mapping between the two ontologies can be digged out by constructing the conditional probability tables (CPTs) of the BN using a improved algorithm named I-IPFP based on iterative proportional fitting procedure (IPFP). The basic idea of this framework and algorithm are validated by positive results from computer experiments.

  16. Information Theory for Analyzing Neural Networks

    Sørngård, Bård


    The goal of this thesis was to investigate how information theory could be used to analyze artificial neural networks. For this purpose, two problems, a classification problem and a controller problem were considered. The classification problem was solved with a feedforward neural network trained with backpropagation, the controller problem was solved with a continuous-time recurrent neural network optimized with evolution.Results from the classification problem shows that mutual information ...

  17. Fast Algorithms for Convolutional Neural Networks

    Lavin, Andrew; Gray, Scott


    Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3x3 filters. We ...

  18. Adaptive optimization and control using neural networks

    Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.


    Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.

  19. Modelling Microwave Devices Using Artificial Neural Networks

    Andrius Katkevičius


    Full Text Available Artificial neural networks (ANN have recently gained attention as fast and flexible equipment for modelling and designing microwave devices. The paper reviews the opportunities to use them for undertaking the tasks on the analysis and synthesis. The article focuses on what tasks might be solved using neural networks, what challenges might rise when using artificial neural networks for carrying out tasks on microwave devices and discusses problem-solving techniques for microwave devices with intermittent characteristics.Article in Lithuanian

  20. Adaptive Control Based On Neural Network

    Wei, Sun; Lujin, Zhang; Jinhai, Zou; Siyi, Miao


    In this paper, the adaptive control based on neural network is studied. Firstly, a neural network based adaptive robust tracking control design is proposed for robotic systems under the existence of uncertainties. In this proposed control strategy, the NN is used to identify the modeling uncertainties, and then the disadvantageous effects caused by neural network approximating error and external disturbances in robotic system are counteracted by robust controller. Especially the proposed cont...

  1. Sequential optimizing investing strategy with neural networks

    Ryo Adachi; Akimichi Takemura


    In this paper we propose an investing strategy based on neural network models combined with ideas from game-theoretic probability of Shafer and Vovk. Our proposed strategy uses parameter values of a neural network with the best performance until the previous round (trading day) for deciding the investment in the current round. We compare performance of our proposed strategy with various strategies including a strategy based on supervised neural network models and show that our procedure is co...

  2. Extended Kalman Filter Based Neural Networks Controller For Hot Strip Rolling mill

    The present paper deals with the application of an Extended Kalman filter based adaptive Neural-Network control scheme to improve the performance of a hot strip rolling mill. The suggested Neural Network model was implemented using Bayesian Evidence based training algorithm. The control input was estimated iteratively by an on-line extended Kalman filter updating scheme basing on the inversion of the learned neural networks model. The performance of the controller is evaluated using an accurate model estimated from real rolling mill input/output data, and the usefulness of the suggested method is proved

  3. Boolean Factor Analysis by Attractor Neural Network

    Frolov, A. A.; Húsek, Dušan; Muraviev, I. P.; Polyakov, P.Y.


    Roč. 18, č. 3 (2007), s. 698-707. ISSN 1045-9227 R&D Projects: GA AV ČR 1ET100300419; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * dimensionality reduction * features clustering * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.769, year: 2007

  4. Artificial neural networks in nuclear medicine

    An analysis of the accessible literature on the diagnostic applicability of artificial neural networks in coronary artery disease and pulmonary embolism appears to be comparative to the diagnosis of experienced doctors dealing with nuclear medicine. Differences in the employed models of artificial neural networks indicate a constant search for the most optimal parameters, which could guarantee the ultimate accuracy in neural network activity. The diagnostic potential within systems containing artificial neural networks proves this calculation tool to be an independent or/and an additional device for supporting a doctor's diagnosis of artery disease and pulmonary embolism. (author)

  5. Fuzzy neural network theory and application

    Liu, Puyin


    This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. Special emphasis is placed on the fundamental concepts and architecture analysis of fuzzy neural networks. The book is unique in treating all kinds of fuzzy neural networks and their learning algorithms and universal approximations, and employing simulation examples which are carefully designed to he

  6. The application of Bayesian networks in natural hazard analyses

    K. Vogel


    Full Text Available In natural hazards we face several uncertainties due to our lack of knowledge and/or the intrinsic randomness of the underlying natural processes. Nevertheless, deterministic analysis approaches are still widely used in natural hazard assessments, with the pitfall of underestimating the hazard with potentially disastrous consequences. In this paper we show that the Bayesian network approach offers a flexible framework for capturing and expressing a broad range of different uncertainties as those encountered in natural hazard assessments. Although well studied in theory, the application of Bayesian networks on real-world data is often not straightforward and requires specific tailoring and adaption of existing algorithms. We demonstrate by way of three case studies (a ground motion model for a seismic hazard analysis, a flood damage assessment, and a landslide susceptibility study the applicability of Bayesian networks across different domains showcasing various properties and benefits of the Bayesian network framework. We offer suggestions as how to tackle practical problems arising along the way, mainly concentrating on the handling of continuous variables, missing observations, and the interaction of both. We stress that our networks are completely data-driven, although prior domain knowledge can be included if desired.

  7. Neural networks for nuclear spectroscopy

    Keller, P.E.; Kangas, L.J.; Hashem, S.; Kouzes, R.T. [Pacific Northwest Lab., Richland, WA (United States)] [and others


    In this paper two applications of artificial neural networks (ANNs) in nuclear spectroscopy analysis are discussed. In the first application, an ANN assigns quality coefficients to alpha particle energy spectra. These spectra are used to detect plutonium contamination in the work environment. The quality coefficients represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with quality coefficients by an expert and used to train the ANN expert system. Our investigation shows that the expert knowledge of spectral quality can be transferred to an ANN system. The second application combines a portable gamma-ray spectrometer with an ANN. In this system the ANN is used to automatically identify, radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perception and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perception for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been tested with data generated by Monte Carlo simulations and with field data from sodium iodide and Germanium detectors. With the ANN approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples. This approach is useful in situations that require fast response where precise quantification is less important.

  8. Chess Endgames and Neural Networks

    Haworth, Guy McCrossan; Velliste, Meel


    The existence of endgame databases challenges us to extract higher-grade information and knowledge from their basic data content. Chess players, for example, would like simple and usable endgame theories if such holy grail exists: endgame experts would like to provide such insights and be inspired by computers to do so. Here, we investigate the use of artificial neural networks (NNs) to mine these databases and we report on a first use of NNs on KPK. The results encourage us to suggest furthe...

  9. Neural Network based Consumption Forecasting

    Madsen, Per Printz


    active participation in the future smart grid environment. One of the main obstacles for making optimal energy consumption is to have good predictions of the future energy consumption. This study is based on real consumption data from eight houses in Denmark. There are designed two different prediction...... models. It is shown that both of the predictions model produce a better consumption prediction then a naïve model. Seen in this perspective is it concluded that it is possible to use Artificial Neural Networks for predicting the energy consumption in ordinary family houses....

  10. Artificial Neural Networks An Introduction

    Priddy, Kevin L


    This tutorial text provides the reader with an understanding of artificial neural networks (ANNs) and their application, beginning with the biological systems which inspired them, through the learning methods that have been developed and the data collection processes, to the many ways ANNs are being used today. The material is presented with a minimum of math (although the mathematical details are included in the appendices for interested readers), and with a maximum of hands-on experience. All specialized terms are included in a glossary. The result is a highly readable text that will teach t

  11. Bayesian网中的独立关系%The Independence Relations in Bayesian Networks

    王飞; 刘大有; 卢奕男; 薛万欣


    Bayesian networks are compact representation of joint probabilistic distribution. Independence is soul of Bayesian networks because it enables to save storage space,to reduce computational complexity and to simplify knowledge acquisition and modeling. In this paper,we discuss three kinds of independences in Bayesian networks :conditional independence,context-specific independence and causal influence independence.

  12. Dynamic Bayesian Networks for Cue Integration

    Paul Maier; Frederike Petzschner


    If we want to understand how humans use contextual cues to solve tasks such as estimating distances from optic flow during path integration, our models need to represent the available information and formally describe how these representations are processed. In particular the temporal dynamics need to be incorporated, since it has been shown that humans exploit short-term experience gained in previous trials (Petzschner und Glasauer, 2011). Existing studies often use a Bayesian approach to mo...

  13. Three dimensional living neural networks

    Linnenberger, Anna; McLeod, Robert R.; Basta, Tamara; Stowell, Michael H. B.


    We investigate holographic optical tweezing combined with step-and-repeat maskless projection micro-stereolithography for fine control of 3D positioning of living cells within a 3D microstructured hydrogel grid. Samples were fabricated using three different cell lines; PC12, NT2/D1 and iPSC. PC12 cells are a rat cell line capable of differentiation into neuron-like cells NT2/D1 cells are a human cell line that exhibit biochemical and developmental properties similar to that of an early embryo and when exposed to retinoic acid the cells differentiate into human neurons useful for studies of human neurological disease. Finally induced pluripotent stem cells (iPSC) were utilized with the goal of future studies of neural networks fabricated from human iPSC derived neurons. Cells are positioned in the monomer solution with holographic optical tweezers at 1064 nm and then are encapsulated by photopolymerization of polyethylene glycol (PEG) hydrogels formed by thiol-ene photo-click chemistry via projection of a 512x512 spatial light modulator (SLM) illuminated at 405 nm. Fabricated samples are incubated in differentiation media such that cells cease to divide and begin to form axons or axon-like structures. By controlling the position of the cells within the encapsulating hydrogel structure the formation of the neural circuits is controlled. The samples fabricated with this system are a useful model for future studies of neural circuit formation, neurological disease, cellular communication, plasticity, and repair mechanisms.

  14. Neural Network Controlled Visual Saccades

    Johnson, Jeffrey D.; Grogan, Timothy A.


    The paper to be presented will discuss research on a computer vision system controlled by a neural network capable of learning through classical (Pavlovian) conditioning. Through the use of unconditional stimuli (reward and punishment) the system will develop scan patterns of eye saccades necessary to differentiate and recognize members of an input set. By foveating only those portions of the input image that the system has found to be necessary for recognition the drawback of computational explosion as the size of the input image grows is avoided. The model incorporates many features found in animal vision systems, and is governed by understandable and modifiable behavior patterns similar to those reported by Pavlov in his classic study. These behavioral patterns are a result of a neuronal model, used in the network, explicitly designed to reproduce this behavior.

  15. Current trends in Bayesian methodology with applications

    Upadhyay, Satyanshu K; Dey, Dipak K; Loganathan, Appaia


    Collecting Bayesian material scattered throughout the literature, Current Trends in Bayesian Methodology with Applications examines the latest methodological and applied aspects of Bayesian statistics. The book covers biostatistics, econometrics, reliability and risk analysis, spatial statistics, image analysis, shape analysis, Bayesian computation, clustering, uncertainty assessment, high-energy astrophysics, neural networking, fuzzy information, objective Bayesian methodologies, empirical Bayes methods, small area estimation, and many more topics.Each chapter is self-contained and focuses on

  16. Video Traffic Prediction Using Neural Networks

    Miloš Oravec


    Full Text Available In this paper, we consider video stream prediction for application in services likevideo-on-demand, videoconferencing, video broadcasting, etc. The aim is to predict thevideo stream for an efficient bandwidth allocation of the video signal. Efficient predictionof traffic generated by multimedia sources is an important part of traffic and congestioncontrol procedures at the network edges. As a tool for the prediction, we use neuralnetworks – multilayer perceptron (MLP, radial basis function networks (RBF networksand backpropagation through time (BPTT neural networks. At first, we briefly introducetheoretical background of neural networks, the prediction methods and the differencebetween them. We propose also video time-series processing using moving averages.Simulation results for each type of neural network together with final comparisons arepresented. For comparison purposes, also conventional (non-neural prediction isincluded. The purpose of our work is to construct suitable neural networks for variable bitrate video prediction and evaluate them. We use video traces from [1].

  17. Implementation of an Adaptive Learning System Using a Bayesian Network

    Yasuda, Keiji; Kawashima, Hiroyuki; Hata, Yoko; Kimura, Hiroaki


    An adaptive learning system is proposed that incorporates a Bayesian network to efficiently gauge learners' understanding at the course-unit level. Also, learners receive content that is adapted to their measured level of understanding. The system works on an iPad via the Edmodo platform. A field experiment using the system in an elementary school…

  18. Nursing Home Care Quality: Insights from a Bayesian Network Approach

    Goodson, Justin; Jang, Wooseung; Rantz, Marilyn


    Purpose: The purpose of this research is twofold. The first purpose is to utilize a new methodology (Bayesian networks) for aggregating various quality indicators to measure the overall quality of care in nursing homes. The second is to provide new insight into the relationships that exist among various measures of quality and how such measures…

  19. A Structure Learning Algorithm for Bayesian Network Using Prior Knowledge

    徐俊刚; 赵越; 陈健; 韩超


    Learning structure from data is one of the most important fundamental tasks of Bayesian network research. Particularly, learning optional structure of Bayesian network is a non-deterministic polynomial-time (NP) hard problem. To solve this problem, many heuristic algorithms have been proposed, and some of them learn Bayesian network structure with the help of different types of prior knowledge. However, the existing algorithms have some restrictions on the prior knowledge, such as quality restriction and use restriction. This makes it difficult to use the prior knowledge well in these algorithms. In this paper, we introduce the prior knowledge into the Markov chain Monte Carlo (MCMC) algorithm and propose an algorithm called Constrained MCMC (C-MCMC) algorithm to learn the structure of the Bayesian network. Three types of prior knowledge are defined: existence of parent node, absence of parent node, and distribution knowledge including the conditional probability distribution (CPD) of edges and the probability distribution (PD) of nodes. All of these types of prior knowledge are easily used in this algorithm. We conduct extensive experiments to demonstrate the feasibility and effectiveness of the proposed method C-MCMC.

  20. Exploiting sensitivity analysis in Bayesian networks for consumer satisfaction study

    Jaronski, W.; Bloemer, J.M.M.; Vanhoof, K.; Wets, G.


    The paper presents an application of Bayesian network technology in a empirical customer satisfaction study. The findings of the study should provide insight as to the importance of product/service dimensions in terms of the strength of their influence on overall satisfaction. To this end we apply a

  1. Neural Networks for Emotion Classification

    Sun, Yafei


    It is argued that for the computer to be able to interact with humans, it needs to have the communication skills of humans. One of these skills is the ability to understand the emotional state of the person. This thesis describes a neural network-based approach for emotion classification. We learn a classifier that can recognize six basic emotions with an average accuracy of 77% over the Cohn-Kanade database. The novelty of this work is that instead of empirically selecting the parameters of the neural network, i.e. the learning rate, activation function parameter, momentum number, the number of nodes in one layer, etc. we developed a strategy that can automatically select comparatively better combination of these parameters. We also introduce another way to perform back propagation. Instead of using the partial differential of the error function, we use optimal algorithm; namely Powell's direction set to minimize the error function. We were also interested in construction an authentic emotion databases. This...

  2. The Laplacian spectrum of neural networks

    Siemon ede Lange


    Full Text Available The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these ‘conventional’ graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network’s structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks.

  3. Drift chamber tracking with neural networks

    Lindsey, C.S.; Denby, B.; Haggerty, H.


    We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed.

  4. Extrapolation limitations of multilayer feedforward neural networks

    Haley, Pamela J.; Soloway, Donald


    The limitations of backpropagation used as a function extrapolator were investigated. Four common functions were used to investigate the network's extrapolation capability. The purpose of the experiment was to determine whether neural networks are capable of extrapolation and, if so, to determine the range for which networks can extrapolate. The authors show that neural networks cannot extrapolate and offer an explanation to support this result.

  5. Drift chamber tracking with neural networks

    We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed

  6. Coherence resonance in bursting neural networks

    Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J.


    Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal—a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.

  7. Differential gene co-expression networks via Bayesian biclustering models

    Gao, Chuan; Zhao, Shiwen; McDowell, Ian C.; Brown, Christopher D.; Barbara E Engelhardt


    Identifying latent structure in large data matrices is essential for exploring biological processes. Here, we consider recovering gene co-expression networks from gene expression data, where each network encodes relationships between genes that are locally co-regulated by shared biological mechanisms. To do this, we develop a Bayesian statistical model for biclustering to infer subsets of co-regulated genes whose covariation may be observed in only a subset of the samples. Our biclustering me...

  8. Bayesian variable selection and data integration for biological regulatory networks

    Jensen, Shane T; Chen, Guang; Stoeckert, Jr, Christian J.


    A substantial focus of research in molecular biology are gene regulatory networks: the set of transcription factors and target genes which control the involvement of different biological processes in living cells. Previous statistical approaches for identifying gene regulatory networks have used gene expression data, ChIP binding data or promoter sequence data, but each of these resources provides only partial information. We present a Bayesian hierarchical model that integrates all three dat...

  9. Artificial Neural Network Modeling of Forest Tree Growth

    Gordon, C


    The problem of modeling forest tree growth curves with an artificial neural network (NN) is examined. The NN parametric form is shown to be a suitable model if each forest tree plot is assumed to consist of several differently growing sub-plots. The predictive Bayesian approach is used in estimating the NN output. Data from the correlated curve trend (CCT) experiments are used. The NN predictions are compared with those of one of the best parametric solutions, the Schnute model. Analysis of variance (ANOVA) methods are used to evaluate whether any observed differences are statistically significant. From a Frequentist perspective the differences between the Schnute and NN approach are found not to be significant. However, a Bayesian ANOVA indicates that there is a 93% probability of the NN approach producing better predictions on average.


    Şeker, Murat; E. Selim YILDIRIM; BERKAY, Ahmet


    Examples of successful applications in Artificial Intelligence (AI) field; With financial applications, Control, Communication, Processing Radar signals, Pattern Recognition, general DSP application, Nonlinear Systems can be given. In the financial applications, generally back propagation (Feedforwared) algorithms of the Neural Network (NN) uses. In this application, backpropagation algorithms applied to Multi Layer Feedforward Neural Network for the future estimations of foreign currency exc...