Elsevier S & T

Neural Networks and Pattern Recognition

Omidvar, Omid; Dayhoff, Judith

In stock
No reviews
37.500 KD inc. VAT
License
Table of contents
  • Cover
  • Contentsv
  • Prefaceix
  • Contributorsxiii
  • Chapter 1. Pulse-Coupled Neural Networks1
  • 1. Introduction2
  • 2. Basic Model3
  • 3. Multiple Pulses10
  • 4. Multiple Receptive Field Inputs13
  • 5. Time Evolution of Two Cells13
  • 6. Space to Time18
  • 7. Linking Waves and Time Scales21
  • 8. Groups22
  • 9. Invariances25
  • 10. Segmentation34
  • 11. Adaptation44
  • 12. Time to Space48
  • 13. Implementations50
  • 14. Integration into Systems51
  • 15. Concluding Remarks53
  • 16. References54
  • Chapter 2. A Neural Network Model for Optical Flow Computation57
  • 1. Introduction57
  • 2. Theoretical Background59
  • 3. Discussion on the Reformulation62
  • 4. Choosing Regularization Parameters63
  • 5. A Recurrent Neural Network Model65
  • 6. Experiments68
  • 7. Comparison to Other Work68
  • 8. Summary and Discussion72
  • 9. References74
  • Chapter 3. Temporal Pattern Matching Using an Artificial Neural Network77
  • 1. Introduction77
  • 2. Solving Optimization Problems Using the Hopfield Network79
  • 3. Dynamic Time Warping Using Hopfield Network81
  • 4. Computer Simulation Results88
  • 5. Conclusions95
  • 6. References103
  • Chapter 4. Patterns of Dynamic Activity and Timing in Neural Network Processing105
  • 1. Introduction105
  • 2. Dynamic Networks108
  • 3. Chaotic Attractors and Attractor Locking114
  • 4. Developing Multiple Attractors120
  • 5. Attractor Basins and Dynamic Binary Networks124
  • 6. Time Delay Mechanisms and Attractor Training129
  • 7. Timing of Action Potentials in Impulse Trains131
  • 8. Discussion134
  • 9. Acknowledgments136
  • 10. References136
  • Chapter 5. A Macroscopic Model of Oscillation in Ensembles of Inhibitory and Excitatory Neurons143
  • 1. Introduction143
  • 2. A Macroscopic Model for Cell Assemblies146
  • 3. Interactions between Two Neural Groups151
  • 4. Stability of Equilibrium States156
  • 5. Oscillation Frequency Estimation159
  • 6. Experimental Validation161
  • 7. Conclusion162
  • 8. Appendix166
  • 9. References166
  • Chapter 6. Finite State Machines and Recurrent Neural Networks„Automata and Dynamical Systems Appr171
  • 1. Introduction171
  • 2. State Machines173
  • 3. Dynamical Systems175
  • 4. Recurrent Neural Networks177
  • 5. RNN as a State Machine179
  • 6. RNN as a Collection of Dynamical Systems186
  • 7. RNN with Two State Neurons191
  • 8. ExperimentsŒLearning Loops of FSM201
  • 9. Discussion211
  • 10. References215
  • Chapter 7. Biased Random-Walk Learning: A Neurobiological Correlate to Trial-and-Error221
  • 1. Introduction221
  • 2. Hebb's Rule222
  • 3. Theoretical Learning Rules225
  • 4. Biological Evidence231
  • 5. Conclusions234
  • 6. Acknowledgments234
  • 7. References235
  • Chapter 8. Using SONNET 1 to Segment Continuous Sequences of Items245
  • 1. Introduction245
  • 2. Learning Isolated and Embedded Spatial Patterns250
  • 3. Storing Items with Decreasing Activity252
  • 4. The LTM Invariance Principle254
  • 5. Using Rehearsal to Process Arbitrarily Long Lists258
  • 6. Implementing the LTM Invariance Principle260
  • 7. Resetting Items Once They Can Be Classified264
  • 8. Properties of a Classifying System267
  • 9. Simulations274
  • 10. Discussion280
  • 11. References281
  • Chapter 9. On the Use of High-Level Petri Nets in the Modeling of Biological Neural Networks285
  • 1. Introduction285
  • 2. Fundamentals of PNs287
  • 3. Modeling of Biological Neural Systems with High-Level PNs292
  • 4. New/Modified Elements Added to HPNs to Model BNNs296
  • 5. Example of a BNN: The Olfactory Bulb299
  • 6. Conclusions307
  • 7. References307
  • Chapter 10. Locally Recurrent Networks: The Gamma Operator, Properties, and Extensions311
  • 1. Introduction311
  • 2. Linear Finite Dimensional Memory Structures312
  • 3. The Gamma Neural Network317
  • 4. Applications of the Gamma Memory320
  • 5. Interpretations of the Gamma Memory322
  • 6. Laguerre and Gamma II Memories330
  • 7. Analog VLSI Implementations of the Gamma Filter335
  • 8. Conclusions337
  • 9. References340
  • Index345
Book details
  • Vendor Elsevier S & T
  • SKU 9780125264204
  • ISBN-13 9780080512617
  • Author Omidvar, Omid; Dayhoff, Judith
  • Category Computers
  • Subject Neural Networks

Do you have questions about this book?

Ask an expert!

Description eBook delivery & access Reviews
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.

Key Features
* 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