Elements of Artificial Neural Networks
by Mehrotra, Mohan, Ranka
ISBN: | Copyright 1996
Instructor Requests
| Expand/Collapse All | |
|---|---|
| Contents (pg. vii) | |
| Preface (pg. xiii) | |
| Chapter 1. Introduction (pg. 1) | |
| 1.1 History of Neural Networks (pg. 4) | |
| 1.2 Structure and Function of a Single Neuron (pg. 7) | |
| 1.3 Neural Net Architectures (pg. 16) | |
| 1.4 Neural Learning (pg. 22) | |
| 1.5 What Can Neural Networks Be Used for? (pg. 24) | |
| 1.6 Evaluation of Networks (pg. 35) | |
| 1.7 Implementation (pg. 38) | |
| 1.8 Conclusion (pg. 39) | |
| 1.9 Exercises (pg. 41) | |
| Chapter 2. Supervised Learning: Single-Layer Networks (pg. 43) | |
| 2.1 Perceptrons (pg. 43) | |
| 2.2 Linear Separability (pg. 45) | |
| 2.3 Perceptron Training Algorithm (pg. 46) | |
| 2.4 Guarantee of Success (pg. 52) | |
| 2.5 Modifications (pg. 54) | |
| 2.6 Conclusion (pg. 61) | |
| 2.7 Exercises (pg. 62) | |
| Chapter 3. Supervised Learning: Multilayer Networks I (pg. 65) | |
| 3.1 Multilevel Discrimination (pg. 66) | |
| 3.2 Preliminaries (pg. 67) | |
| 3.3 Backpropagation Algorithm (pg. 70) | |
| 3.4 Setting the Parameter Values (pg. 79) | |
| 3.5 Theoretical Results* (pg. 88) | |
| 3.6 Accelerating the Learning Process (pg. 93) | |
| 3.7 Applications (pg. 98) | |
| 3.8 Conclusion (pg. 105) | |
| 3.9 Exercises (pg. 106) | |
| Chapter 4. Supervised Learning: Multilayer Networks II (pg. 111) | |
| 4.1 Madalines (pg. 111) | |
| 4.2 Adaptive Multilayer Networks (pg. 116) | |
| 4.3 Prediction Networks (pg. 136) | |
| 4.4 Radial Basis Functions (pg. 141) | |
| 4.5 Polynomial Networks (pg. 149) | |
| 4.6 Regularization (pg. 153) | |
| 4.7 Conclusion (pg. 154) | |
| 4.8 Exercises (pg. 155) | |
| Chapter 5. Unsupervised Learning (pg. 157) | |
| 5.1 Winner-Take-All Networks (pg. 161) | |
| 5.2 Learning Vector Quantizers (pg. 173) | |
| 5.3 Counterpropagation Networks (pg. 176) | |
| 5.4 Adaptive Resonance Theory (pg. 180) | |
| 5.5 Topologically Organized Networks (pg. 187) | |
| 5.6 Distance-Based Learning (pg. 201) | |
| 5.7 Neocognitron (pg. 204) | |
| 5.8 Principal Component Analysis Networks (pg. 208) | |
| 5.9 Conclusion (pg. 213) | |
| 5.10 Exercises (pg. 214) | |
| Chapter 6. Associative Models (pg. 217) | |
| 6.1 Non-iterative Procedures for Association (pg. 219) | |
| 6.2 Hopfield Networks (pg. 227) | |
| 6.3 Brain-State-in-a-Box Network (pg. 244) | |
| 6.4 Boltzmann Machines (pg. 249) | |
| 6.5 Hetero-associators (pg. 255) | |
| 6.6 Conclusion (pg. 262) | |
| 6.7 Exercises (pg. 263) | |
| Chapter 7. Optimization Methods (pg. 267) | |
| 7.1 Optimization using Hopfield Networks (pg. 269) | |
| 7.2 Iterated Gradient Descent (pg. 279) | |
| 7.3 Simulated Annealing (pg. 280) | |
| 7.4 Random Search (pg. 285) | |
| 7.5 Evolutionary Computation (pg. 287) | |
| 7.6 Conclusion (pg. 300) | |
| 7.7 Exercises (pg. 302) | |
| A. Appendix (pg. 307) | |
| A.1 Calculus (pg. 307) | |
| A.2 Linear Algebra (pg. 309) | |
| A.3 Statistics (pg. 310) | |
| B. Appendix (pg. 315) | |
| B.1 Iris Data (pg. 315) | |
| B.2 Classification of Myoelectric Signals (pg. 316) | |
| B.3 Gold Prices (pg. 318) | |
| B.4 Clustering Animal Features (pg. 319) | |
| B.5 3-D Corners, Grid and Approximation (pg. 319) | |
| B.6 Eleven-City Traveling Salesperson Problem (Distances) (pg. 323) | |
| B.7 Daily Stock Prices of Three Companies, over the Same Period (pg. 324) | |
| B.8 Spiral Data (pg. 327) | |
| Bibliography (pg. 331) | |
| Index (pg. 339) | |
| Contents (pg. vii) | |
| Preface (pg. xiii) | |
| Chapter 1. Introduction (pg. 1) | |
| Chapter 2. Supervised Learning: Single-Layer Networks (pg. 43) | |
| Chapter 3. Supervised Learning: Multilayer Networks I (pg. 65) | |
| Chapter 4. Supervised Learning: Multilayer Networks II (pg. 111) | |
| Chapter 5. Unsupervised Learning (pg. 157) | |
| Chapter 6. Associative Models (pg. 217) | |
| Chapter 7. Optimization Methods (pg. 267) | |
| A. Appendix (pg. 307) | |
| B. Appendix (pg. 315) | |
| Bibliography (pg. 331) | |
| Index (pg. 339) | |
| Contents (pg. vii) | |
| Preface (pg. xiii) | |
| Chapter 1. Introduction (pg. 1) | |
| Chapter 2. Supervised Learning: Single-Layer Networks (pg. 43) | |
| Chapter 3. Supervised Learning: Multilayer Networks I (pg. 65) | |
| Chapter 4. Supervised Learning: Multilayer Networks II (pg. 111) | |
| Chapter 5. Unsupervised Learning (pg. 157) | |
| Chapter 6. Associative Models (pg. 217) | |
| Chapter 7. Optimization Methods (pg. 267) | |
| A. Appendix (pg. 307) | |
| B. Appendix (pg. 315) | |
| Bibliography (pg. 331) | |
| Index (pg. 339) | |
| Contents (pg. vii) | |
| Preface (pg. xiii) | |
| Chapter 1. Introduction (pg. 1) | |
| Chapter 2. Supervised Learning: Single-Layer Networks (pg. 43) | |
| Chapter 3. Supervised Learning: Multilayer Networks I (pg. 65) | |
| Chapter 4. Supervised Learning: Multilayer Networks II (pg. 111) | |
| Chapter 5. Unsupervised Learning (pg. 157) | |
| Chapter 6. Associative Models (pg. 217) | |
| Chapter 7. Optimization Methods (pg. 267) | |
| A. Appendix (pg. 307) | |
| B. Appendix (pg. 315) | |
| Bibliography (pg. 331) | |
| Index (pg. 339) | |
Kishan Mehrotra
Professor and Chair, Department of Electrical Engineering and Computer Science at Syracuse University.
Chilukuri Mohan
Professor of Electrical Engineering and Computer Science at Syracuse University.
Sanjay Ranka
Professor of Computer & Information Science & Engineering at the University of Florida.| Instructors Only | |
|---|---|
|
You must have an instructor account and submit a request to access instructor materials for this book.
|
|
eTextbook
Go paperless today! Available online anytime, nothing to download or install.
Features
|
