UID:
almahu_9948025875402882
Format:
1 online resource (369 p.)
ISBN:
1-281-03343-X
,
9786611033439
,
0-08-051261-5
Content:
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* Inclu
Note:
Description based upon print version of record.
,
Front Cover; Neural Networks and Pattern Recognition; Copyright Page; Contents; Preface; Contributors; Chapter 1. Pulse-Coupled Neural Networks; 1. Introduction; 2. Basic Model; 3. Multiple Pulses; 4. Multiple Receptive Field Inputs; 5. Time Evolution of Two Cells; 6. Space to Time; 7. Linking Waves and Time Scales; 8. Groups; 9. Invariances; 10. Segmentation; 11. Adaptation; 12. Time to Space; 13. Implementations; 14. Integration into Systems; 15. Concluding Remarks; 16. References; Chapter 2. A Neural Network Model for Optical Flow Computation; 1. Introduction; 2. Theoretical Background
,
3. Discussion on the Reformulation4. Choosing Regularization Parameters; 5. A Recurrent Neural Network Model; 6. Experiments; 7. Comparison to Other Work; 8. Summary and Discussion; 9. References; Chapter 3. Temporal Pattern Matching Using an Artificial Neural Network; 1. Introduction; 2. Solving Optimization Problems Using the Hopfield Network; 3. Dynamic Time Warping Using Hopfield Network; 4. Computer Simulation Results; 5. Conclusions; 6. References; Chapter 4. Patterns of Dynamic Activity and Timing in Neural Network Processing; 1. Introduction; 2. Dynamic Networks
,
3. Chaotic Attractors and Attractor Locking4. Developing Multiple Attractors; 5. Attractor Basins and Dynamic Binary Networks; 6. Time Delay Mechanisms and Attractor Training; 7. Timing of Action Potentials in Impulse Trains; 8. Discussion; 9. Acknowledgments; 10. References; Chapter 5. A Macroscopic Model of Oscillation in Ensembles of Inhibitory and Excitatory Neurons; 1. Introduction; 2. A Macroscopic Model for Cell Assemblies; 3. Interactions between Two Neural Groups; 4. Stability of Equilibrium States; 5. Oscillation Frequency Estimation; 6. Experimental Validation; 7. Conclusion
,
6. Acknowledgments7. References; Chapter 8. Using SONNET 1 to Segment Continuous Sequences of Items; 1. Introduction; 2. Learning Isolated and Embedded Spatial Patterns; 3. Storing Items with Decreasing Activity; 4. The LTM Invariance Principle; 5. Using Rehearsal to Process Arbitrarily Long Lists; 6. Implementing the LTM Invariance Principle; 7. Resetting Items Once They Can Be Classified; 8. Properties of a Classifying System; 9. Simulations; 10. Discussion; 11. References; Chapter 9. On the Use of High-Level Petri Nets in the Modeling of Biological Neural Networks; 1. Introduction
,
2. Fundamentals of PNs
,
English
Additional Edition:
ISBN 0-12-526420-8
Language:
English
