Neural Networks for Control

Front Cover
W. Thomas Miller, Paul J. Werbos, Richard S. Sutton
MIT Press, 1995 - Computers - 524 pages
0 Reviews

Neural Networks for Control highlights key issues in learning control and identifiesresearch directions that could lead to practical solutions for control problems in criticalapplication domains. It addresses general issues of neural network based control and neural networklearning with regard to specific problems of motion planning and control in robotics, and takes upapplication domains well suited to the capabilities of neural network controllers. The appendixdescribes seven benchmark control problems.W. Thomas Miller, III is Professor of Electrical andComputer Engineering at the University of New Hampshire. Richard S. Sutton works for GTELaboratories Incorporated. Paul J. Werbos is Program Director for Neuroengineering at the NationalScience Foundation.Contributors: Andrew G. Barto. Ronald J. Williams. Paul J. Werbos. Kumpati S.Narendra. L. Gordon Kraft, III, David P. Campagna. Mitsuo Kawato. Bartlett W. Met. Christopher G.Atkeson, David J. Reinkensmeyer. Derrick Nguyen, Bernard Widrow. James C. Houk, Satinder P. Singh,Charles Fisher. Judy A. Franklin, Oliver G. Selfridge. Arthur C. Sanderson. Lyle H. Ungar. CharlesC. Jorgensen, C. Schley. Martin Herman, James S. Albus, Tsai-Hong Hong. Charles W. Anderson, W.Thomas Miller, III.

 

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

An Overview
5
Computational Schemes and Neural Network Mod
9
Overview of Designs and Capabilities
59
Adaptive State Representation and Estimation Using
97
Adaptive Control using Neural Networks
115
A Summary Comparison of CMAC Neural Network
143
Recent Advances in Numerical Techniques for Large
171
VisionBased Robot Motion Planning
229
An Adaptive Sensorimotor Network Inspired by
301
Some New Directions for Adaptive Control Theory
349
Applications of Neural Networks in Robotics
365
A Bioreactor Benchmark for Adaptive Network
387
A Neural Network Baseline Problem for Control
403
Intelligent Control for Multiple Autonomous Under
427
A A Challenging Set of Control Problems
475
Index
511

Using Associative ContentAddressable Memories
255
An example of Self
287
Copyright

Common terms and phrases

ACAM action network adaptive control adaptive critic adjusted aircraft algorithm applications approach architecture assumed backpropagation Barto behavior cerebellar cerebellum chapter class of models climbing fiber command complex computation connectionist connectionist network connectionist research control problems control system control theory convergence critic network Cybernetics derivatives described discussed dynamic programming dynamical systems engineering equation error evaluation example experiences feedback feedforward function gradient Hinton identification IEEE Transactions implemented input inverse inverse dynamics Kawato layer learning algorithm learning control learning methods loop mapping modules motor program movement Narendra neural net neural network neurons noise obstacles optimal parallel fiber parameter estimation pattern performance planner planning position Purkinje cells real-time recurrent network reinforcement learning represent representation robot Rumelhart sensor shown in figure signals simulation structure supervised learning Sutton target task Technical Report techniques tion torque units update values variables vector vehicle velocity Werbos Widrow world model

References to this book

Nonlinear System Identification: From Classical Approaches to Neural ...
Oliver Nelles
Limited preview - 2001
Computational Intelligence in Control Engineering
Robert E. King
Limited preview - 1999
All Book Search results »

About the author (1995)

W. Thomas Miller, III is Professor of Electrical and Computer Engineering at the University of New Hampshire.

PAUL JOHN WERBOS is a Program Director in the Engineering Directorate of the National Science Foundation as well as Past President of the International Neural Network Society. Previously, he developed and evaluated large-scale forecasting models at the Energy Information Administration of the Department of Energy, using backpropagation and other techniques discussed in this book. He has contributed, as a writer or editor, to several books on neural networks and has published more than forty journal articles and conference papers on a wide range of subjects.

Richard S. Sutton is Professor of Computing Science and AITF Chair in Reinforcement Learning and Artificial Intelligence at the University of Alberta, and also Distinguished Research Scientist at DeepMind.

Bibliographic information

QR code for Neural Networks for Control
TitleNeural Networks for Control
Bradford Books
Neural Network Modeling and Connectionism
Neural Networks for Control
EditorsW. Thomas Miller, Paul J. Werbos, Richard S. Sutton
Editionillustrated, reprint, revised
PublisherMIT Press, 1995
ISBN026263161X, 9780262631617
Length524 pages
Subjects › 

Computers / General
Psychology / Cognitive Psychology & Cognition
  
Export CitationBiBTeX EndNote RefMan