+612 9045 4394
 
CHECKOUT
Backpropagation : Theory, Architectures, and Applications - Yves Chauvin

Backpropagation

Theory, Architectures, and Applications

By: Yves Chauvin (Editor), David E. Rumelhart (Editor)

Paperback

Published: 1st February 1995
Ships: 7 to 10 business days
7 to 10 business days
RRP $334.99
$231.95
31%
OFF
or 4 easy payments of $57.99 with Learn more

Composed of three sections, this book presents the most popular training algorithm for neural networks: backpropagation. The first section presents the theory and principles behind backpropagation as seen from different perspectives such as statistics, machine learning, and dynamical systems. The second presents a number of network architectures that may be designed to match the general concepts of Parallel Distributed Processing with backpropagation learning. Finally, the third section shows how these principles can be applied to a number of different fields related to the cognitive sciences, including control, speech recognition, robotics, image processing, and cognitive psychology. The volume is designed to provide both a solid theoretical foundation and a set of examples that show the versatility of the concepts. Useful to experts in the field, it should also be most helpful to students seeking to understand the basic principles of connectionist learning and to engineers wanting to add neural networks in general -- and backpropagation in particular -- to their set of problem-solving methods.

Prefacep. vii
Acknowledgmentsp. ix
Introductionp. 1
Backpropagation: The Basic Theoryp. 1
Referencesp. 33
Conclusionp. 33
Phoneme Recognition Using Time-Delay Neural Networksp. 35
Abstractp. 35
Acknowledgmentp. 59
Referencesp. 59
Automated Aircraft Flare and Touchdown Control Using Neural Networksp. 63
Introductionp. 63
Automated Aircraft Flare and Touchdown Control Using Neural Networksp. 63
Referencesp. 98
Acknowledgmentsp. 98
Introductionp. 99
Recurrent Backpropagation Networksp. 99
Recurrent Backpropagation Networksp. 99
Acknowledgementsp. 130
Gradient Evaluationp. 130
Stability of Error Back- Propagation Equationp. 132
Pseudocodep. 133
Referencesp. 134
A Focused Backpropagation Algorithm for Temporal Pattern Recognitionp. 137
Introductionp. 137
A Focused Backpropagation Algorithm for Temporal Pattern Recognitionp. 137
Appendix: Derivation of the Focused Back- Propagation Algorithmp. 166
Acknowledgementsp. 168
Referencesp. 168
Nonlinear Control with Neural Networksp. 171
Introductionp. 171
Nonlinear Control with Neural Networksp. 171
Summaryp. 187
Referencesp. 188
Acknowledgementsp. 188
Forward Models: Supervised Learning with a Distal Teacherp. 189
Abstractp. 189
Conclusionsp. 230
Acknowledgementsp. 231
Referencesp. 232
p. 234
p. 235
p. 236
Introductionp. 237
Backpropagation: Some Comments and Variationsp. 237
Referencesp. 269
Graded State Machines: The Representation of Temporal Contingencies in Feedback Networksp. 273
Graded State Machines: The Representation of Temporal Contingencies in Feedback Networksp. 273
Introductionp. 274
Acknowledgmentp. 311
Referencesp. 311
Spatial Coherence as an Internal Teacher for a Neural Networkp. 313
Abstractp. 313
Introductionp. 314
Conclusionsp. 343
Acknowledgementsp. 344
the Mutual Information Gradient in the Binary Casep. 344
the Mutual Information Gradient in the Continuous Casep. 346
Referencesp. 348
Connectionist Modeling and Control of Finite State Systems Given Partial State Informationp. 351
Connectionist Modeling and Control of Finite State Systems Given Partial State Informationp. 351
Introductionp. 351
Referencesp. 386
Backpropagation and Unsupervised Learning in Linear Networksp. 389
Introductionp. 389
Appendix: Some Mathematical Proofsp. 424
Referencesp. 430
Acknowledgmentp. 430
Introductionp. 433
Gradient-Based Learning Algorithms for Recurrent Networks and Their Computational Complexityp. 433
Acknowledgmentp. 480
Referencesp. 480
A. Appendixp. 482
Introductionp. 487
When Neural Networks Play Sherlock Holmesp. 487
When Neural Networks Play Sherlock Holmesp. 487
Appendixp. 505
Acknowledgementsp. 505
Referencesp. 507
Gradient Descent Learning Algorithms: A Unified Perspectivep. 509
Introductionp. 509
Gradient Descent Learning Algorithms: A Unified Perspectivep. 509
Appendixp. 533
Conclusionp. 533
Acknowledgementsp. 539
Referencesp. 539
Author Indexp. 543
Subject Indexp. 549
Table of Contents provided by Publisher. All Rights Reserved.

ISBN: 9780805812596
ISBN-10: 0805812598
Series: Developments in Connectionist Theory
Audience: Professional
Format: Paperback
Language: English
Number Of Pages: 576
Published: 1st February 1995
Publisher: Taylor & Francis Inc
Country of Publication: US
Dimensions (cm): 24.13 x 15.88  x 3.81
Weight (kg): 0.93
Edition Number: 1