Backpropagation

View this topic in
Backpropagation is a common method of teaching artificial neural networks how to perform a given task. (Wikipedia.org)






Conferences related to Backpropagation

Back to Top

2013 12th IEEE International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)

Cognitive Informatics (CI) is a cutting-edge and multidisciplinary research field that tackles the fundamental problems shared by modern informatics, computing, AI, cybernetics, computational intelligence, cognitive science, intelligence science, neuropsychology, brain science, systems science, software engineering, knowledge engineering, cognitive robots, scientific philosophy, cognitive linguistics, life sciences, and cognitive computing.

  • 2012 11th IEEE International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)

    Cognitive informatics and Cognitive Computing are a transdisciplinary enquiry on the internal information processing mechanisms and processes of the brain and their engineering applications in cognitive computers, computational intelligence, cognitive robots, cognitive systems, and in the AI, IT, and software industries. The 11th IEEE Int l Conference on Cognitive Informatics and Cognitive Computing (ICCI*CC 12) focuses on the theme of e-Brain and Cognitive Computers.

  • 2011 10th IEEE International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)

    Cognitive Informatics and Cognitive Computing are a transdisciplinary enquiry on the internal information processing mechanisms and processes of the brain and their engineering applications in cognitive computers, computational intelligence, cognitive robots, cognitive systems, and in the AI, IT, and software industries. The 10th IEEE Int l Conference on Cognitive Informatics and Cognitive Computing (ICCI*CC 11) focuses on the theme of Cognitive Computers and the e-Brain.

  • 2010 9th IEEE International Conference on Cognitive Informatics (ICCI)

    Cognitive Informatics (CI) is a cutting-edge and transdisciplinary research area that tackles the fundamental problems shared by modern informatics, computing, AI, cybernetics, computational intelligence, cognitive science, neuropsychology, medical science, systems science, software engineering, telecommunications, knowledge engineering, philosophy, linguistics, economics, management science, and life sciences.

  • 2009 8th IEEE International Conference on Cognitive Informatics (ICCI)

    The 8th IEEE International Conference on Cognitive Informatics (ICCI 09) focuses on the theme of Cognitive Computing and Semantic Mining. The objectives of ICCI'09 are to draw attention of researchers, practitioners, and graduate students to the investigation of cognitive mechanisms and processes of human information processing, and to stimulate the international effort on cognitive informatics research and engineering applications.

  • 2008 7th IEEE International Conference on Cognitive Informatics (ICCI)

    The 7th IEEE International Conference on Cognitive Informatics (ICCI 08) focuses on the theme of Cognitive Computers and Computational Intelligence. The objectives of ICCI 08 are to draw attention of researchers, practitioners and graduate students to the investigation of cognitive mechanisms and processes of human information processing, and to stimulate the international effort on cognitive informatics research and engineering applications.

  • 2007 6th IEEE International Conference on Cognitive Informatics (ICCI)

  • 2006 5th IEEE International Conference on Cognitive Informatics (ICCI)


2013 15th International Conference on Transparent Optical Networks (ICTON)

ICTON addresses applications of transparent and all optical technologies in telecommunication networks, systems, and components. ICTON topics are well balanced between basic optics and network engineering. Interactions between those two groups of professionals are a valuable merit of conference. ICTON combines high level invited talks with carefully selected regular submissions.

  • 2012 14th International Conference on Transparent Optical Networks (ICTON)

    ICTON addresses applications of transparent and all optical technologies in telecommunication networks, systems, and components. ICTON topics are well balanced between basic optics and network engineering. Interactions between those two groups of professionals are a valuable merit of conference. ICTON combines high level invited talks with carefully selected regular submissions.

  • 2011 13th International Conference on Transparent Optical Networks (ICTON)

    ICTON addresses applications of transparent and all optical technologies in telecommunication networks, systems, and components. ICTON topics are well balanced between basic optics and network engineering. Interactions between those two groups of professionals are a valuable merit of conference. ICTON combines high level invited talks with carefully selected regular submissions.

  • 2010 12th International Conference on Transparent Optical Networks (ICTON)

    ICTON addresses applications of transparent and all optical technologies in telecommunication networks, systems, and components. ICTON topics are well balanced between basic optics and network engineering. Interactions between those two groups of professionals are a valuable merit of conference. ICTON combines high level invited talks with carefully selected regular submissions.

  • 2009 11th International Conference on Transparent Optical Networks (ICTON 2009)

    ICTON scope is concentrated on the applications of transparent and all-optical technologies in telecommunication networks, systems, and components. ICTON topics are balanced between basic optics and network engineering. Interactions between those two groups of professionals are an important merit of conference. ICTON combines high level invited talks with regular submissions.


2013 26th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)

This is a general Electrical and Computer Engineering Conference which encompasses all aspects of these fields.

  • 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)

    On behalf of the organizing committee of the 2012 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), it is with great pleasure to invite you to the 25th anniversary of this conference. CCECE is the annual flagship of IEEE Canada, and over the past 24 years it has been established as a major forum in various areas of electrical and computer engineering for researchers from Canada and around the world. The silver anniversary of CCECE in Montreal is an important milestone in the history of this conference, and the organizing committee members are trying hard to make it a memorable one.

  • 2011 24th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)

    The 2011 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE 2011) will be held in Niagara Falls, Ontario, Canada from May 8 11, 2011. CCECE 2011 provides a forum for the presentation of electrical and computer engineering research and development from Canada and around the world. Papers are invited, in French or English, for the following symposia.

  • 2010 IEEE 23rd Canadian Conference on Electrical and Computer Engineering - CCECE

    CCECE 2010 provides researchers, students, and practicing professionals in the area of Electrical and Computer Engineering with a Canadian venue in which they can present the latest technological advancements and discoveries. CCECE 2010 will feature papers presented from a broad range of areas in Electrical and Computer Engineering.

  • 2009 IEEE 22nd Canadian Conference on Electrical and Computer Engineering - CCECE

    CCECE provides researchers, students, and practicing professionals in the area of Electrical and Computer Engineering with a Canadian venue in which they can present the latest technological advancements and discoveries. It is also a valuable opportunity to network, exchange ideas, strengthen existing partnerships and foster new collaborations. CCECE 2009 will feature 7 mini-symposia with papers presented from a broad range of areas in Electrical and Computer Engineering. There will be tutorial sessions in


2013 International Joint Conference on Neural Networks (IJCNN 2013 - Dallas)

Neural Networks

  • 2012 International Joint Conference on Neural Networks (IJCNN 2012 - Brisbane)

    The annual IJCNN is the premier international conference in the field of neural networks.

  • 2011 International Joint Conference on Neural Networks (IJCNN 2011 - San Jose)

    IJCNN 2011 will include paper presentations, tutorials, workships, panels, special sessions and competitions on topics related to neural networks, including: Neural network theory and models; neural network applications; computational neuroscience; neurocognitive models; neuroengineering; neuroinformatics; neuroevolution; collective intelligence; embodied robotics; artificial life, etc.

  • 2010 International Joint Conference on Neural Networks (IJCNN 2010 - Barcelona)

  • 2009 International Joint Conference on Neural Networks (IJCNN 2009 - Atlanta)

    IJCNN is the premier international conference in the area of neural networks theory, analysis and applications. It is organized by the International Neural Networks Society (INNS) and sponsored jointly by INNS and the IEEE Computational Intelligence Society. This is an exemplary collaboration between the two leading societies on neural networks and it provides a solid foundation for the future extensive development of the field.



Periodicals related to Backpropagation

Back to Top

Engineering in Medicine and Biology Magazine, IEEE

Both general and technical articles on current technologies and methods used in biomedical and clinical engineering; societal implications of medical technologies; current news items; book reviews; patent descriptions; and correspondence. Special interest departments, students, law, clinical engineering, ethics, new products, society news, historical features and government.


Neural Networks, IEEE Transactions on

Devoted to the science and technology of neural networks, which disclose significant technical knowledge, exploratory developments, and applications of neural networks from biology to software to hardware. Emphasis is on artificial neural networks.



Most published Xplore authors for Backpropagation

Back to Top

Xplore Articles related to Backpropagation

Back to Top

Backpropagation Modification in Monte-Carlo Game Tree Search

Fan Xie; Zhiqing Liu 2009 Third International Symposium on Intelligent Information Technology Application, 2009

The Algorithm UCT, proposed by Kocsys et al, which apply multi-armed bandit problem into the tree-structured search space, achieves some remarkable success in some challenging fields. For UCT algorithm, Monte-Carlo simulations are performed with the guidance of UCB1 formula, which are averaged to evaluate a specified action. We observe that, as more simulations are performed, later ones usually lead to ...


Recurrent neural networks for identification of nonlinear systems

Xuemei Ren; Shumin Fei Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187), 2000

A type of recurrent neural network is discussed which provides the potential for the modelling of unknown nonlinear systems with multi-inputs and multi- outputs. The proposed network is a generalization of the network described by Elman (1989). It is shown that the proposed network with appropriate neurons in the context layer can model unknown nonlinear systems. Based on a PID-like ...


The comparison and selection about the improving backpropagation algorithms of the neural networks based on MATLAB language

Xiangjun Gao; Xinzheng Zhang; Zhongjuan Li Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788), 2004

All kinds of modified BP algorithms in the MATLAB's neural networks toolbox are discussed in the optimization techniques and compared with speed and memory. Different problem types applied to those algorithms are proposed.


Training artificial neural networks for short-term electricity price forecasting

E. N. Chogumaira; T. Hiyama 2009 Transmission & Distribution Conference & Exposition: Asia and Pacific, 2009

This paper present a comparative study of training approaches for artificial neural network (ANN) used in forecasting short-term wholesale electricity prices. High probability of volatility in wholesale electricity prices and trends that are generally non-uniform create challenges when forecasting future prices using simple backpropagation feedforward ANN. A number of ANN architectures and training methods have been proposed for a variety ...


Training recurrent network with block-diagonal approximated Levenberg-Marquardt algorithm

Lai-Wan Chan; Chi-Cheong Szeto Neural Networks, 1999. IJCNN '99. International Joint Conference on, 1999

We propose the block-diagonal matrix to approximate the Hessian matrix in the Levenberg-Marquardt method in the training of neural networks. Two weight updating strategies, namely asynchronous and synchronous updating methods, were investigated. Asynchronous method updates weights of one block at a time while synchronous method updates all weights at the same time. Variations of these two methods, which involves the ...


More Xplore Articles

Educational Resources on Backpropagation

Back to Top

eLearning

Backpropagation Modification in Monte-Carlo Game Tree Search

Fan Xie; Zhiqing Liu 2009 Third International Symposium on Intelligent Information Technology Application, 2009

The Algorithm UCT, proposed by Kocsys et al, which apply multi-armed bandit problem into the tree-structured search space, achieves some remarkable success in some challenging fields. For UCT algorithm, Monte-Carlo simulations are performed with the guidance of UCB1 formula, which are averaged to evaluate a specified action. We observe that, as more simulations are performed, later ones usually lead to ...


Recurrent neural networks for identification of nonlinear systems

Xuemei Ren; Shumin Fei Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187), 2000

A type of recurrent neural network is discussed which provides the potential for the modelling of unknown nonlinear systems with multi-inputs and multi- outputs. The proposed network is a generalization of the network described by Elman (1989). It is shown that the proposed network with appropriate neurons in the context layer can model unknown nonlinear systems. Based on a PID-like ...


The comparison and selection about the improving backpropagation algorithms of the neural networks based on MATLAB language

Xiangjun Gao; Xinzheng Zhang; Zhongjuan Li Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788), 2004

All kinds of modified BP algorithms in the MATLAB's neural networks toolbox are discussed in the optimization techniques and compared with speed and memory. Different problem types applied to those algorithms are proposed.


Training artificial neural networks for short-term electricity price forecasting

E. N. Chogumaira; T. Hiyama 2009 Transmission & Distribution Conference & Exposition: Asia and Pacific, 2009

This paper present a comparative study of training approaches for artificial neural network (ANN) used in forecasting short-term wholesale electricity prices. High probability of volatility in wholesale electricity prices and trends that are generally non-uniform create challenges when forecasting future prices using simple backpropagation feedforward ANN. A number of ANN architectures and training methods have been proposed for a variety ...


Training recurrent network with block-diagonal approximated Levenberg-Marquardt algorithm

Lai-Wan Chan; Chi-Cheong Szeto Neural Networks, 1999. IJCNN '99. International Joint Conference on, 1999

We propose the block-diagonal matrix to approximate the Hessian matrix in the Levenberg-Marquardt method in the training of neural networks. Two weight updating strategies, namely asynchronous and synchronous updating methods, were investigated. Asynchronous method updates weights of one block at a time while synchronous method updates all weights at the same time. Variations of these two methods, which involves the ...


More eLearning Resources

IEEE-USA E-Books

  • Multilayer Neural Networks and Backpropagation

    A computationally effective method for training the multilayer perceptrons is the backpropagation algorithm, which is regarded as a landmark in the development of neural network. This chapter presents two different learning methods, batch learning and online learning, on the basis of how the supervised learning of the multilayer perceptron is actually performed. The essence of backpropagation learning is to encode an input-output mapping into the synaptic weights and thresholds of a multilayer perceptron. It is hoped that the network becomes well trained so that it learns enough about the past to generalize to the future. The chapter concludes with cross-validation and generalization. Cross-validation is appealing particularly when people have to design a large neural network with good generalization as the goal in different ways. Generalization is assumed that the test data are drawn from the same population used to generate the training data.

  • Multilayered Feedforward Neural Networks (MFNNs) and Backpropagation Learning Algorithms

    Two-layered Neural Networks Example 4.1: XOR Neural Network Backpropagation (BP) Algorithms for MFNN Deriving BP Algorithm Using Variational Principle Momentum BP Algorithm A Summary of BP Learning Algorithm Some Issues in BP Learning Algorithm Concluding Remarks Problems

  • Backpropagation in non-feedforward networks

    Backpropagation is a powerful supervised learning rule for networks with hidden units. However, as originally introduced, and as described in Chapter 4, it is limited to feedforward networks. In this chapter we derive the generalization of backpropagation to non-feedforward networks. This generalization happens to take a very simple form: the error propagation network can be obtained simply by linearizing, and then transposing, the network to be trained. Networks with feedback necessarily raise the problem of stability. We prove that the error propagation network is always stable when training is performed. We also derive a sufficient condition for the stability of the non-feedforward neural network, and we discuss the problem of the possible existence of multiple stable states. Finally, we present some experimental results on the use of back propagation in non-feedforward networks.

  • Radial-Basis Function Networks

    This chapter focuses on the radial-basis function (RBF) network as an alternative to multilayer perceptrons. It will be interesting to find that in a multilayer perceptron, the function approximation is defined by a nested set of weighted summations, while in a RBF network, the approximation is defined by a single weighted sum. The chapter focuses on the use of a Gaussian function as the radial-basis function. The reason behind the choice of the Gaussian function as the radial-basis function in building RBF networks is that it has many desirable properties, which will become evident as the discussion progresses. It is important to point out that RBF networks and multilayer perceptrons can be trained in alternative ways besides those presented. For multilayer perceptrons, the backpropagation algorithm is simple to compute locally and it performs stochastic gradient descent in weight space when the algorithm is implemented in an online learning mode.

  • Learning in Multilayer Models

    Most neural network programs for personal computers simply control a set of fixed, canned network-layer algorithms with pulldown menus. This new tutorial offers hands-on neural network experiments with a different approach. A simple matrix language lets users create their own neural networks and combine networks, and this is the only currently available software permitting combined simulation of neural networks together with other dynamic systems such as robots or physiological models. The enclosed student version of DESIRE/NEUNET differs from the full system only in the size of its data area and includes a screen editor, compiler, color graphics, help screens, and ready-to-run examples. Users can also add their own help screens and interactive menus.The book provides an introduction to neural networks and simulation, a tutorial on the software, and many complete programs including several backpropagation schemes, creeping random search, competitive learning with and without adaptive-resonance function and "conscience," counterpropagation, nonlinear Grossberg-type neurons, Hopfield-type and bidirectional associative memories, predictors, function learning, biological clocks, system identification, and more.In addition, the book introduces a simple, integrated environment for programming, displays, and report preparation. Even differential equations are entered in ordinary mathematical notation. Users need not learn C or LISP to program nonlinear neuron models. To permit truly interactive experiments, the extra-fast compilation is unnoticeable, and simulations execute faster than PC FORTRAN.The nearly 90 illustrations include block diagrams, computer programs, and simulation-output graphs.Granino A. Kom has been a Professor of Electrical Engineering at the University of Arizona and has worked in the aerospace industry for a decade. He is the author of ten other engineering texts and handbooks.

  • Index

    Artificial Neural Networks (ANNs) offer an efficient method for finding optimal cleanup strategies for hazardous plumes contaminating groundwater by allowing hydrologists to rapidly search through millions of possible strategies to find the most inexpensive and effective containment of contaminants and aquifer restoration. ANNs also provide a faster method of developing systems that classify seismic events as being earthquakes or underground explosions.Farid Dowla and Leah Rogers have developed a number of ANN applications for researchers and students in hydrology and seismology. This book, complete with exercises and ANN algorithms, illustrates how ANNs can be used in solving problems in environmental engineering and the geosciences, and provides the necessary tools to get started using these elegant and efficient new techniques.Following the development of four primary ANN algorithms (backpropagation, self-organizing, radial basis functions, and hopfield networks), and a discussion of important issues in ANN formulation (generalization properties, computer generation of training sets, causes of slow training, feature extraction and preprocessing, and performance evaluation), readers are guided through a series of straightforward yet complex illustrative problems. These include groundwater remediation management, seismic discrimination between earthquakes and underground explosions, automated monitoring for acoustic and seismic sensor data, estimation of seismic sources, geospatial estimation, lithologic classification from geophysical logging, earthquake forecasting, and climate change. Each chapter contains detailed exercises often drawn from field data that use one or more of the four primary ANN algorithms presented.

  • Appendix G: Thirty Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation

    This chapter contains sections titled: Introduction Fundamental Concepts Adaptation  -  The Minimal Disturbance Principle Error Correction Rules  -  Single Threshold Element Error Correction Rules  -  Multi-Element Networks Steepest-Descent Rules  -  Single Threshold Element Steepest-Descent Rules  -  Multi-Element Networks Summary Acknowledgments Bibliography

  • Overview of Designs and Capabilities

    This chapter contains sections titled: Introduction, Supervised Control, Direct Inverse Control, Neural Adaptive Control, Backpropagation Through Time, Adaptive Critics

  • Basics

    Most neural network programs for personal computers simply control a set of fixed, canned network-layer algorithms with pulldown menus. This new tutorial offers hands-on neural network experiments with a different approach. A simple matrix language lets users create their own neural networks and combine networks, and this is the only currently available software permitting combined simulation of neural networks together with other dynamic systems such as robots or physiological models. The enclosed student version of DESIRE/NEUNET differs from the full system only in the size of its data area and includes a screen editor, compiler, color graphics, help screens, and ready-to-run examples. Users can also add their own help screens and interactive menus.The book provides an introduction to neural networks and simulation, a tutorial on the software, and many complete programs including several backpropagation schemes, creeping random search, competitive learning with and without adaptive-resonance function and "conscience," counterpropagation, nonlinear Grossberg-type neurons, Hopfield-type and bidirectional associative memories, predictors, function learning, biological clocks, system identification, and more.In addition, the book introduces a simple, integrated environment for programming, displays, and report preparation. Even differential equations are entered in ordinary mathematical notation. Users need not learn C or LISP to program nonlinear neuron models. To permit truly interactive experiments, the extra-fast compilation is unnoticeable, and simulations execute faster than PC FORTRAN.The nearly 90 illustrations include block diagrams, computer programs, and simulation-output graphs.Granino A. Kom has been a Professor of Electrical Engineering at the University of Arizona and has worked in the aerospace industry for a decade. He is the author of ten other engineering texts and handbooks.

  • Approximate Dynamic Programming and Backpropagation on Timescales

    This chapter contains sections titled: Introduction: Timescales Fundamentals Dynamic Programming Backpropagation Conclusions References



Standards related to Backpropagation

Back to Top

No standards are currently tagged "Backpropagation"


Jobs related to Backpropagation

Back to Top