Conferences related to Neural Networks

Back to Top

2014 IEEE 23rd International Symposium on Industrial Electronics (ISIE)

Control Systems & ApplicationsPower ElectronicsSignal Processing & Computational IntelligenceRobotics & MechatronicsSensors, Actuators & System IntegrationElectrical Machines & DrivesFactory Automation & Industrial InformaticsEmerging Technologies

  • 2012 IEEE 21st International Symposium on Industrial Electronics (ISIE)

    IEEE-ISIE is the largest summer conference of the IEEE Industrial Electronics Society, which is an international forum for presentation and discussion of the state of art in Industrial Electronics and related areas.

  • 2011 IEEE 20th International Symposium on Industrial Electronics (ISIE)

    Industrial electronics, power electronics, power converters, electrical machines and drives, signal processing, computational intelligence, mechatronics, robotics, telecommuniction, power systems, renewable energy, factory automation, industrial informatics.

  • 2010 IEEE International Symposium on Industrial Electronics (ISIE 2010)

    Application of electronics and electrical sciences for the enhancement of industrial and manufacturing processes. Latest developments in intelligent and computer control systems, robotics, factory communications and automation, flexible manufacturing, data acquisition and signal processing, vision systems, and power electronics.

  • 2009 IEEE International Symposium on Industrial Electronics (ISIE 2009)

    The purpose of the IEEE international conference is to provide a forum for presentation and discussion of the state-of art of Industrial Electronics and related areas.


2014 IEEE International Conference on Systems, Man and Cybernetics - SMC

SMC2014 targets advances in Systems Science and Engineering, Human-Machine Systems, and Cybernetics involving state-of-art technologies interacting with humans to provide an enriching experience and thereby improving the quality of lives including theories, methodologies, and emerging applications.

  • 2013 IEEE International Conference on Systems, Man and Cybernetics - SMC

    SMC 2013 targets advances in Systems Science and Engineering Human-machine Systems and Cybernetics involving state-of-the-art technologies interacting with humans to provide an enriching experience and thereby improving the quality of lives including theories, methodologies and emerging applications.

  • 2012 IEEE International Conference on Systems, Man and Cybernetics - SMC

    Theory, research and technology advances including applications in all aspects of systems science and engineering, human machine systems, and emerging cybernetics.

  • 2011 IEEE International Conference on Systems, Man and Cybernetics - SMC

    Theory, research, and technology advances including applications in all aspects of systems science and engineering, human machine systems, and emerging cybernetics.

  • 2010 IEEE International Conference on Systems, Man and Cybernetics - SMC

    The 2010 IEEE International Conference on Systems, Man, and Cybernetics (SMC2010) provides an international forum that brings together those actively involved in areas of interest to the IEEE Systems, Man, and Cybernetics Society, to report on up-to-the-minute innovations and developments, to summarize the state-of-the-art, and to exchange ideas and advances in all aspects of systems science and engineering, human machine systems, and cybernetics.

  • 2009 IEEE International Conference on Systems, Man and Cybernetics - SMC

    The 2009 IEEE International Conference on Systems, Man, and Cybernetics (SMC2009) provides an international forum that brings together those actively involved in areas of interest to the IEEE Systems, Man, and Cybernetics Society, to report on up-to-the-minute innovations and developments, to summarize the state-of-the-art, and to exchange ideas and advances in all aspects of systems science and engineering, human machine systems, and cybernetics.


2014 IEEE International Symposium on Circuits and Systems (ISCAS)

The IEEE International Symposium on Circuits and Systems (ISCAS) is the flagship conference of the IEEE Circuits and Systems Society and the world’s premier networking forum in the highly active fields of theory, design and implementation of circuits and systems.ISCAS 2014 will have a special focus on nano/bio circuits and systems applied to enhancing living and lifestyles, and seeks to address multidisciplinary challenges in healthcare and well-being, the environment and climate change.

  • 2013 IEEE International Symposium on Circuits and Systems (ISCAS)

    The Symposium will focus on circuits and systems employing nanodevices (both extremely scaled CMOS and non-CMOS devices) and circuit fabrics (mixture of standard CMOS and evolving nano-structure elements) and their implementation cost, switching speed, energy efficiency, and reliability. The ISCAS 2010 will include oral and poster sessions; tutorials given by experts in state-of-the-art topics; and special sessions, with the aim of complementing the regular program with topics of particular interest to the community that cut across and beyond disciplines traditionally represented at ISCAS.

  • 2012 IEEE International Symposium on Circuits and Systems - ISCAS 2012

    2012 International Symposium on Circuits and Systems (ISCAS 2012) aims at providing the world's premier forum of leading researchers in circuits and systems areas from academia and industries, especially focusing on Convergence of BINET (BioInfoNanoEnviro Tech.) which represents IT, NT and ET and leading Human Life Revolutions. Prospective authors are invited to submit papers of their original works emphasizing contributions beyond the present state of the art. We also welcome proposals on special tuto

  • 2011 IEEE International Symposium on Circuits and Systems (ISCAS)

    The IEEE International Symposium on Circuits and Systems (ISCAS) is the world's premier networking forum of leading researchers in the highly active fields of theory, design and implementation of circuits and systems.

  • 2010 IEEE International Symposium on Circuits and Systems - ISCAS 2010

    ISCAS is a unique conference dealing with circuits and systems. It's the yearly "rendez-vous" of leading researchers, coming both from academia and industry, in the highly active fields of theory, design and implementation of circuits and systems. The Symposium will focus on circuits and systems for high quality life and consumer technologies, including mobile communications, advanced multimedia systems, sensor networks and Nano-Bio Circuit Fabrics and Systems.

  • 2009 IEEE International Symposium on Circuits and Systems - ISCAS 2009

    Analog Signal Processing, Biomedical Circuits and Systems, Blind Signal Processing, Cellular Neural Networks and Array Computing, Circuits and Systems for Communications, Computer-Aided Network Design, Digital Signal Processing, Life-Science Systems and Applications, Multimedia Systems and Applications, Nanoelectronics and Gigascale Systems, Neural Systems and Applications, Nonlinear Circuits and Applications, Power Systems and Power Electronic Circuits, Sensory Systems, Visual Signal Processing and Communi


IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society

Applications of power electronics, artificial intelligence, robotics, and nanotechnology in electrification of automotive, military, biomedical, and utility industries.

  • IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society

    Industrial and manufacturing theory and applications of electronics, controls, communications, instrumentation and computational intelligence.

  • IECON 2012 - 38th Annual Conference of IEEE Industrial Electronics

    The conference will be focusing on industrial and manufacturing theory and applications of electronics,power, sustainable development, controls, communications, instrumentation and computational intelligence.

  • IECON 2011 - 37th Annual Conference of IEEE Industrial Electronics

    industrial applications of electronics, control, robotics, signal processing, computational and artificial intelligence, sensors and actuators, instrumentation electronics, computer networks, internet and multimedia technologies.

  • IECON 2010 - 36th Annual Conference of IEEE Industrial Electronics

    IECON is an international conference on industrial applications of electronics, control, robotics, signal processing, computational and artificial intelligence, sensors and actuators, instrumentation electronics, computer networks, internet and multimedia technologies. The objectives of the conference are to provide high quality research and professional interactions for the advancement of science, technology, and fellowship.

  • IECON 2009 - 35th Annual Conference of IEEE Industrial Electronics

    Applications of electronics, instrumentation, control and computational intelligence to industrial and manufacturing systems and process. Major themes include power electronics, drives, sensors, actuators, signal processing, motion control, robotics, mechatronics, factory and building automation, and informatics. Emerging technologies and applications such as renewable energy, electronics reuse, and education.


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.


More Conferences

Periodicals related to Neural Networks

Back to Top

Circuits and Systems for Video Technology, IEEE Transactions on

Video A/D and D/A, display technology, image analysis and processing, video signal characterization and representation, video compression techniques and signal processing, multidimensional filters and transforms, analog video signal processing, neural networks for video applications, nonlinear video signal processing, video storage and retrieval, computer vision, packet video, high-speed real-time circuits, VLSI architecture and implementation for video technology, multiprocessor systems--hardware and software-- ...


Circuits and Systems I: Regular Papers, IEEE Transactions on

Part I will now contain regular papers focusing on all matters related to fundamental theory, applications, analog and digital signal processing. Part II will report on the latest significant results across all of these topic areas.


Circuits and Systems Magazine, IEEE


Computational Biology and Bioinformatics, IEEE/ACM Transactions on

Specific topics of interest include, but are not limited to, sequence analysis, comparison and alignment methods; motif, gene and signal recognition; molecular evolution; phylogenetics and phylogenomics; determination or prediction of the structure of RNA and Protein in two and three dimensions; DNA twisting and folding; gene expression and gene regulatory networks; deduction of metabolic pathways; micro-array design and analysis; proteomics; ...


Computational Intelligence Magazine, IEEE

The IEEE Computational Intelligence Magazine (CIM) publishes peer-reviewed articles that present emerging novel discoveries, important insights, or tutorial surveys in all areas of computational intelligence design and applications.


More Periodicals

Most published Xplore authors for Neural Networks

Back to Top

Xplore Articles related to Neural Networks

Back to Top

Free Tuition for Community College: A Role for the Tech Community?

David Alan Grier Computer, 2016

The Obama administration recently made three major announcements about a proposal to make community college tuition free. This shift offers the tech community an opportunity to share its unique viewpoint on the cost and structure of community colleges. The Web extra at https://youtu.be/ZR_PxPlngKE is an audio recording of author David Alan Grier reading this Computing Education column.


A BP neural network model for SWCC considering consolidation stress

Tian Dongfang; Wang Shimei; Xiao Shirong 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, 2010

Soil-Water Characteristic Curve (SWCC) plays an important role in theoretical research and practical application. At present, SWCC can be obtained from experiments. The experimental results are inconvenient for practical application. Some models are presented to fit experimental results, such as Gardner model, V-G model, etc. Recent experimental results show that besides water content, the consolidation stress has influence on SWCC ...


Online feedforward calculation for plasma shape control in tokamaks with superconducting coils

Michael L. Walker; Matthew J. Lanctot; Sang-Hee Hahn 2016 IEEE Conference on Control Applications (CCA), 2016

In this work, we describe a method for online calculation of the feedforward component of a combined feedforward/feedback simultaneous control of plasma current and boundary shape in tokamaks with superconducting control coils. Use of this online feedforward calculation method is intended to significantly reduce the feedback gains required for plasma shape and current control. It also supports graceful degradation of ...


Neural Networks For Impulse Removal In NTSC TV Receivers

J. C. Pearson IEEE 1992 International Conference on Consumer Electronics Digest of Technical Papers, 1992

First Page of the Article ![](/xploreAssets/images/absImages/00697109.png)


Nonlinear blind source separation based on radial basis function

Ding Liu; Yan Zhao Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788), 2004

Radial basis function (RBF) neural network is used as a de-mixing system for nonlinear blind source separation (BSS). The nonlinear mixing mapping is assumed to exist and able to be approximated using RBF network. The object criterion is based on the maximum entropy (ME) approach. To ensure the entropy of the outputs has upper bounded, a special sigmoid function is ...


More Xplore Articles

Educational Resources on Neural Networks

Back to Top

eLearning

Free Tuition for Community College: A Role for the Tech Community?

David Alan Grier Computer, 2016

The Obama administration recently made three major announcements about a proposal to make community college tuition free. This shift offers the tech community an opportunity to share its unique viewpoint on the cost and structure of community colleges. The Web extra at https://youtu.be/ZR_PxPlngKE is an audio recording of author David Alan Grier reading this Computing Education column.


A BP neural network model for SWCC considering consolidation stress

Tian Dongfang; Wang Shimei; Xiao Shirong 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, 2010

Soil-Water Characteristic Curve (SWCC) plays an important role in theoretical research and practical application. At present, SWCC can be obtained from experiments. The experimental results are inconvenient for practical application. Some models are presented to fit experimental results, such as Gardner model, V-G model, etc. Recent experimental results show that besides water content, the consolidation stress has influence on SWCC ...


Online feedforward calculation for plasma shape control in tokamaks with superconducting coils

Michael L. Walker; Matthew J. Lanctot; Sang-Hee Hahn 2016 IEEE Conference on Control Applications (CCA), 2016

In this work, we describe a method for online calculation of the feedforward component of a combined feedforward/feedback simultaneous control of plasma current and boundary shape in tokamaks with superconducting control coils. Use of this online feedforward calculation method is intended to significantly reduce the feedback gains required for plasma shape and current control. It also supports graceful degradation of ...


Neural Networks For Impulse Removal In NTSC TV Receivers

J. C. Pearson IEEE 1992 International Conference on Consumer Electronics Digest of Technical Papers, 1992

First Page of the Article ![](/xploreAssets/images/absImages/00697109.png)


Nonlinear blind source separation based on radial basis function

Ding Liu; Yan Zhao Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788), 2004

Radial basis function (RBF) neural network is used as a de-mixing system for nonlinear blind source separation (BSS). The nonlinear mixing mapping is assumed to exist and able to be approximated using RBF network. The object criterion is based on the maximum entropy (ME) approach. To ensure the entropy of the outputs has upper bounded, a special sigmoid function is ...


More eLearning Resources

IEEE.tv Videos

20 Years of Neural Networks: A Promising Start, A brilliant Future- Video contents
Artificial Neural Networks, Intro
ICASSP 2010 - Advances in Neural Engineering
Large-scale Neural Systems for Vision and Cognition
Spike Timing, Rhythms, and the Effective Use of Neural Hardware
Complex-Valued Neural Networks
Emergent Neural Network in reinforcement learning
Behind Artificial Neural Networks
Deep Learning and the Representation of Natural Data
Complex Valued Neural Networks: Theory and Applications
Spiking Network Algorithms for Scientific Computing - William Severa: 2016 International Conference on Rebooting Computing
Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardware - Emre Neftci: 2016 International Conference on Rebooting Computing
Active Space-Body Perception and Body Enhancement using Dynamical Neural Systems
Overcoming the Static Learning Bottleneck - the Need for Adaptive Neural Learning - Craig Vineyard: 2016 International Conference on Rebooting Computing
High Throughput Neural Network based Embedded Streaming Multicore Processors - Tarek Taha: 2016 International Conference on Rebooting Computing
Recurrent Neural Networks for System Identification, Forecasting and Control
Developing Point-of-Care Technologies
Vladimir Cherkassky - Predictive Learning, Knowledge Discovery and Philosophy of Science
Accelerating Machine Learning with Non-Volatile Memory: Exploring device and circuit tradeoffs - Pritish Narayanan: 2016 International Conference on Rebooting Computing
Uncovering the Neural Code of Learning Control - Jennie Si - WCCI 2012 invited lecture

IEEE-USA E-Books

  • Introduction and Single-Layer Neural Networks

    Neural networks are potentially massively parallel distributed structures and have the ability to learn and generalize. The neuron is the information processing unit of a neural network and the basis for designing numerous neural networks. The most fundamental network architecture is a single-layer neural network, where the single-layer refers to the output layer of computation neurons. This chapter introduces Rosenblatt's neuron. Rosenblatt's perceptron occupies a special place in the historical development of neural networks. The chapter also considers the performance of the perceptron network and is in a position to introduce the perceptron learning rule. This learning rule is an example of supervised training, in which the learning rule is provided with a set of examples of proper network behavior. Finally the chapter further discusses activation function and its types, including a threshold function, or Heaviside function and sigmoid function.

  • Evolving Obstacle Avoidance Behavior in a Robot Arm

    Existing approaches for learning to control a robot arm rely on supervised methods where correct behavior is explicitly given. It is difficult to learn to avoid obstacles using such methods, however, because examples of obstacle avoidance behavior are hard to generate. This paper presents an alternative approach that evolves neural network controllers through genetic algorithms. No input/output examples are necessary, since neuroevolution learns from a single performance measurement over the entire task of grasping an object. The approach is tested in a simulation of the OSCAR-6 robot arm which receives both visual and sensory input. Neural networks evolved to effectively avoid obstacles at various locations to reach random target locations.

  • Neural Units: Concepts, Models, and Learning

    Neurons and Threshold Logic: Some Basic Concepts Neural Threshold Logic Synthesis Adaptation and Learning for Neural Threshold Elements Adaptive Linear Element (Adaline) Adaline with Sigmoidal Functions Networks with Multiple Neurons Concluding Remarks Problems

  • 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.

  • Special Session On Morphogenic Evolutionary Computation

    March 1-3, 1995, San Diego, California Evolutionary programming is one of the predominate algorithms withing the rapidly expanding field of evolutionary computation. These edited contributions to the Fourth Annual Conference on Evolutionary Programming are by leading scientists from academia, industry, and defense. The papers describe both the theory and practical application of evolutionary programming, as well as other methods of evolutionary computation including evolution strategies, genetic algorithms, genetic programming, and cultural algorithms.Topics include :- Novel Areas of Evolutionary Programming and Evolution Strategies.- Evolutionary Computation with Medical Applications.- Issues in Evolutionary Optimization Pattern Discovery, Pattern Recognition, and System Identification.- Hierarchical Levels of Learning.- Self-Adaptation in Evolutionary Computation.- Morphogenic Evolutionary Computation.- Issues in Evolutionary Optimization.- Evolutionary Applications to VLSI and Part Placement.- Applications of Evolutionary Computation to Biology and Biochemistry Control.- Applications of Evolutionary Computation.- Genetic and Inductive Logic Programming.- Genetic Neural Networks.- The Future of Evolutionary Computation.A Bradford Book. Complex Adaptive Systems series

  • 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

  • Index

    Brimming with top articles from experts in signal processing and biomedical engineering, Time Frequency and Wavelets in Biomedical Signal Processing introduces time-frequency, time-scale, wavelet transform methods, and their applications in biomedical signal processing. This edited volume incorporates the most recent developments in the field to illustrate thoroughly how the use of these time-frequency methods is currently improving the quality of medical diagnosis, including technologies for assessing pulmonary and respiratory conditions, EEGs, hearing aids, MRIs, mammograms, X rays, evoked potential signals analysis, neural networks applications, among other topics. Time Frequency and Wavelets in Biomedical Signal Processing will be of particular interest to signal processing engineers, biomedical engineers, and medical researchers. Topics covered include: Time-frequency analysis methods and biomedical applications Wavelets, wavelet packets, and matching pursuits and biomedical applications Wavelets and medical imaging Wavelets, neural networks, and fractals

  • Intelligent Control: An Overview of Techniques

    In many established fields, the label ?>intelligent?> heralds new developments that take issue with some traditional assumptions in research. In the case of intelligent control, an explicit attempt is made to draw inspiration from nature, biology, and artificial intelligence, and a methodology is promoted that is more accepting of heuristics and approximationsï¿¿-ï¿¿and is less insistent on theoretical rigor and completenessï¿¿-ï¿¿than is the case with most research in control science. Beyond such general and abstract features, succinct characterizations of intelligent control are difficult. Extensional treatments are an easier matter. Fuzzy logic, neural networks, genetic algorithms, and expert systems constitute the main areas of the field, with applications to nonlinear identification, nonlinear control design, controller tuning, system optimization, and encapsulation of human operator expertise. Intelligent control is thus no narrow specialization; it furnishes a diverse body of techniques that potentially addresses most of the technical challenges in control systems. It is also important to emphasize that intelligent control is by no means methodologically opposed to theory and analysis. Chapter 6 of this book, for example, discusses some theoretical results for neural networks and fuzzy models as nonlinear approximators Introductory tutorials to the key topics in intelligent control are provided in this chapter. No prior background in these topics is assumed. Examples from ship maneuvering, robotics, and automotive diagnostics help motivate the discussion. (Other chapters in this volume, notably Chapter 16, also outline applications of intelligent control.) General observations on autonomy and adaptationï¿ ¿-ï¿¿two characteristics that are often considered essential to any definition of intelligenceï¿¿-ï¿¿are also included.

  • References

    An unprecedented wealth of data is being generated by genome sequencing projects and other experimental efforts to determine the structure and function of biological molecules. The demands and opportunities for interpreting these data are expanding rapidly. Bioinformatics is the development and application of computer methods for management, analysis, interpretation, and prediction, as well as for the design of experiments. Machine learning approaches (e.g., neural networks, hidden Markov models, and belief networks) are ideally suited for areas where there is a lot of data but little theory, which is the situation in molecular biology. The goal in machine learning is to extract useful information from a body of data by building good probabilistic models--and to automate the process as much as possible.In this book Pierre Baldi and Sÿren Brunak present the key machine learning approaches and apply them to the computational problems encountered in the analysis of biological data. The book is aimed both at biologists and biochemists who need to understand new data-driven algorithms and at those with a primary background in physics, mathematics, statistics, or computer science who need to know more about applications in molecular biology.This new second edition contains expanded coverage of probabilistic graphical models and of the applications of neural networks, as well as a new chapter on microarrays and gene expression. The entire text has been extensively revised.

  • 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.



Standards related to Neural Networks

Back to Top

No standards are currently tagged "Neural Networks"


Jobs related to Neural Networks

Back to Top