Preface | p. vii |
Acknowledgments | p. ix |
Introduction | p. 1 |
Backpropagation: The Basic Theory | p. 1 |
References | p. 33 |
Conclusion | p. 33 |
Phoneme Recognition Using Time-Delay Neural Networks | p. 35 |
Abstract | p. 35 |
Acknowledgment | p. 59 |
References | p. 59 |
Automated Aircraft Flare and Touchdown Control Using Neural Networks | p. 63 |
Introduction | p. 63 |
Automated Aircraft Flare and Touchdown Control Using Neural Networks | p. 63 |
References | p. 98 |
Acknowledgments | p. 98 |
Introduction | p. 99 |
Recurrent Backpropagation Networks | p. 99 |
Recurrent Backpropagation Networks | p. 99 |
Acknowledgements | p. 130 |
Gradient Evaluation | p. 130 |
Stability of Error Back- Propagation Equation | p. 132 |
Pseudocode | p. 133 |
References | p. 134 |
A Focused Backpropagation Algorithm for Temporal Pattern Recognition | p. 137 |
Introduction | p. 137 |
A Focused Backpropagation Algorithm for Temporal Pattern Recognition | p. 137 |
Appendix: Derivation of the Focused Back- Propagation Algorithm | p. 166 |
Acknowledgements | p. 168 |
References | p. 168 |
Nonlinear Control with Neural Networks | p. 171 |
Introduction | p. 171 |
Nonlinear Control with Neural Networks | p. 171 |
Summary | p. 187 |
References | p. 188 |
Acknowledgements | p. 188 |
Forward Models: Supervised Learning with a Distal Teacher | p. 189 |
Abstract | p. 189 |
Conclusions | p. 230 |
Acknowledgements | p. 231 |
References | p. 232 |
| p. 234 |
| p. 235 |
| p. 236 |
Introduction | p. 237 |
Backpropagation: Some Comments and Variations | p. 237 |
References | p. 269 |
Graded State Machines: The Representation of Temporal Contingencies in Feedback Networks | p. 273 |
Graded State Machines: The Representation of Temporal Contingencies in Feedback Networks | p. 273 |
Introduction | p. 274 |
Acknowledgment | p. 311 |
References | p. 311 |
Spatial Coherence as an Internal Teacher for a Neural Network | p. 313 |
Abstract | p. 313 |
Introduction | p. 314 |
Conclusions | p. 343 |
Acknowledgements | p. 344 |
the Mutual Information Gradient in the Binary Case | p. 344 |
the Mutual Information Gradient in the Continuous Case | p. 346 |
References | p. 348 |
Connectionist Modeling and Control of Finite State Systems Given Partial State Information | p. 351 |
Connectionist Modeling and Control of Finite State Systems Given Partial State Information | p. 351 |
Introduction | p. 351 |
References | p. 386 |
Backpropagation and Unsupervised Learning in Linear Networks | p. 389 |
Introduction | p. 389 |
Appendix: Some Mathematical Proofs | p. 424 |
References | p. 430 |
Acknowledgment | p. 430 |
Introduction | p. 433 |
Gradient-Based Learning Algorithms for Recurrent Networks and Their Computational Complexity | p. 433 |
Acknowledgment | p. 480 |
References | p. 480 |
A. Appendix | p. 482 |
Introduction | p. 487 |
When Neural Networks Play Sherlock Holmes | p. 487 |
When Neural Networks Play Sherlock Holmes | p. 487 |
Appendix | p. 505 |
Acknowledgements | p. 505 |
References | p. 507 |
Gradient Descent Learning Algorithms: A Unified Perspective | p. 509 |
Introduction | p. 509 |
Gradient Descent Learning Algorithms: A Unified Perspective | p. 509 |
Appendix | p. 533 |
Conclusion | p. 533 |
Acknowledgements | p. 539 |
References | p. 539 |
Author Index | p. 543 |
Subject Index | p. 549 |
Table of Contents provided by Publisher. All Rights Reserved. |