Neural Networks and Pattern Recognition

Description

This book is one of the most up-to-date and cutting-edge texts available on the rapidly growing application area of neural networks. Neural Networks and Pattern Recognition focuses on the use of neural networksin pattern recognition, a very important application area for neural networks technology. The contributors are widely known and highly respected researchers and practitioners in the field.

Features neural network architectures on the cutting edge of neural network research
Brings together highly innovative ideas on dynamical neural networks
Includes articles written by authors prominent in the neural networks research community
Provides an authoritative, technically correct presentation of each specific technical area

Front Cover 2
Neural Networks and Pattern Recognition 5
Copyright Page 6
Contents 7
Preface 11
Contributors 15
Chapter 1. Pulse-Coupled Neural Networks 19
- 1. Introduction 20
- 2. Basic Model 21
- 3. Multiple Pulses 28
- 5. Time Evolution of Two Cells 31
- 4. Multiple Receptive Field Inputs 31
- 6. Space to Time 36
- 7. Linking Waves and Time Scales 39
- 8. Groups 40

Front Cover 2
Neural Networks and Pattern Recognition 5
Copyright Page 6
Contents 7
Preface 11
Contributors 15
Chapter 1. Pulse-Coupled Neural Networks 19
- 1. Introduction 20
- 2. Basic Model 21
- 3. Multiple Pulses 28
- 5. Time Evolution of Two Cells 31
- 4. Multiple Receptive Field Inputs 31
- 6. Space to Time 36
- 7. Linking Waves and Time Scales 39
- 8. Groups 40
- 9. Invariances 43
- 10. Segmentation 52
- 11. Adaptation 62
- 12. Time to Space 66
- 13. Implementations 68
- 14. Integration into Systems 69
- 15. Concluding Remarks 71
- 16. References 72
Chapter 2. A Neural Network Model for Optical Flow Computation 75
- 1. Introduction 75
- 2. Theoretical Background 77
- 3. Discussion on the Reformulation 80
- 4. Choosing Regularization Parameters 81
- 5. A Recurrent Neural Network Model 83
- 7. Comparison to Other Work 86
- 6. Experiments 86
- 8. Summary and Discussion 90
- 9. References 92
Chapter 3. Temporal Pattern Matching Using an Artificial Neural Network 95
- 1. Introduction 95
- 2. Solving Optimization Problems Using the Hopfield Network 97
- 3. Dynamic Time Warping Using Hopfield Network 99
- 4. Computer Simulation Results 106
- 5. Conclusions 113
- 6. References 121
Chapter 4. Patterns of Dynamic Activity and Timing in Neural Network Processing 123
- 1. Introduction 123
- 2. Dynamic Networks 126
- 3. Chaotic Attractors and Attractor Locking 132
- 4. Developing Multiple Attractors 138
- 5. Attractor Basins and Dynamic Binary Networks 142
- 6. Time Delay Mechanisms and Attractor Training 147
- 7. Timing of Action Potentials in Impulse Trains 149
- 8. Discussion 152
- 9. Acknowledgments 154
- 10. References 154
Chapter 5. A Macroscopic Model of Oscillation in Ensembles of Inhibitory and Excitatory Neurons 161
- 1. Introduction 161
- 2. A Macroscopic Model for Cell Assemblies 164
- 3. Interactions between Two Neural Groups 169
- 4. Stability of Equilibrium States 174
- 5. Oscillation Frequency Estimation 177
- 6. Experimental Validation 179
- 7. Conclusion 180
- 8. Appendix 184
- 9. References 184
Chapter 6. Finite State Machines and Recurrent Neural Networks—Automata and Dynamical Systems Approaches 189
- 1. Introduction 189
- 2. State Machines 191
- 3. Dynamical Systems 193
- 4. Recurrent Neural Networks 195
- 5. RNN as a State Machine 197
- 6. RNN as a Collection of Dynamical Systems 204
- 7. RNN with Two State Neurons 209
- 8. Experiments„Learning Loops of FSM 219
- 9. Discussion 229
- 10. References 233
Chapter 7. Biased Random-Walk Learning: A Neurobiological Correlate to Trial-and-Error 239
- 1. Introduction 239
- 2. Hebb's Rule 240
- 3. Theoretical Learning Rules 243
- 4. Biological Evidence 249
- 6. Acknowledgments 252
- 5. Conclusions 252
- 7. References 253
Chapter 8. Using SONNET 1 to Segment Continuous Sequences of Items 263
- 1. Introduction 263
- 2. Learning Isolated and Embedded Spatial Patterns 268
- 3. Storing Items with Decreasing Activity 270
- 4. The LTM Invariance Principle 272
- 5. Using Rehearsal to Process Arbitrarily Long Lists 276
- 6. Implementing the LTM Invariance Principle 278
- 7. Resetting Items Once They Can Be Classified 282
- 8. Properties of a Classifying System 285
- 9. Simulations 292
- 10. Discussion 298
- 11. References 299
Chapter 9. On the Use of High-Level Petri Nets in the Modeling of Biological Neural Networks 303
- 1. Introduction 303
- 2. Fundamentals of PNs 305
- 3. Modeling of Biological Neural Systems with High-Level PNs 310
- 4. New/Modified Elements Added to HPNs to Model BNNs 314
- 5. Example of a BNN: The Olfactory Bulb 317
- 7. References 325
- 6. Conclusions 325
Chapter 10. Locally Recurrent Networks: The Gamma Operator, Properties, and Extensions 329
- 1. Introduction 329
- 2. Linear Finite Dimensional Memory Structures 330
- 3. The Gamma Neural Network 335
- 4. Applications of the Gamma Memory 338
- 5. Interpretations of the Gamma Memory 340
- 6. Laguerre and Gamma II Memories 348
- 7. Analog VLSI Implementations of the Gamma Filter 353
- 8. Conclusions 355
- 9. References 358

Author's affiliation

Omid Omidvar: University of the District of Columbia
Judith Dayhoff: Institute of System Research, University of M

Description

TOC

Reviews (0)

Author's affiliation