Preface 1. Introduction Objectives History Applications Biological Inspiration Further Reading 2. Neuron Model and Network Architectures Objectives Theory and Examples Notation Neuron Model Single-Input Neuron Transfer Functions Multiple-Input Neuron Network Architectures A Layer of Neurons Multiple Layers of Neurons Recrrent Networks Summary of Results Solved Problems Epilogue Exercises 3. An Illustrative Example Objectives Theory and Examples Problem Statement Perceptron Two-Input Case Pattern Recognition Example Hamming Network Feedforward Layer Recurrent Layer Hopfield Network Epilogue Exercise 4. Perceptron Learning Rule Objectives Theory and Examples Learning Rules Perceptron Architecture Single-Neuron Perceptron Multiple-Neuron Perceptron Perceptron Learning Rule Test Problem Constructing Learning Rules Unified Learning Rule Training Multiple-Neuron Perceptrons Proof of Convergence Notation Proof Limitations Summary of Results Solved Problems Epilogue Further Reading Exercises 5. Signal and Weight Vector Spaces Objectives Theory and Examples Linear Vector Spaces Linear independence Spanning a Space Inner Product Norm Orthogonality Gram-Schmidt Orthogonalization Vector Expansions Reciprocal Basis Vectors Summary of Results Solved Problems Epilogue Further Reading Exercises 6. Linear Transformations for Neural Networks Objectives Theory and Examples Linear Transformations Matrix Representations Change of Basis Eigenvalues and Eigenvectors Diagonalization Summary of Results Solved Problems Epilogue Further Reading Exercises 7. Supervised Hebbian Learning Objectives Theory and Examples Linear Associator The Hebb Rule Performance Analysis Pseudoinverse Rule Application Variations of Hebbian Learning Summary of Results Solved Problems Epilogue Further Reading Exercises 8. Performance Surfaces and Optimum Points Objectives Theory and Examples Taylor Series Vector Case Directional Derivatives Minima Necessary Conditions for Optimality First-Order Conditions Second-Order Conditions Quadratic Functions Eigensystem of the Hessian Summary of Results Solved Problems Epilogue Further Reading Exercises 9. Performance Optimization Objectives Theory and Examples Steepest Descent Stable Learning Rates Minimizing Along a Line Newton's Method Conjugate Gradient Summary of Results Solved Problems Epilogue Further Reading Exercises 10. Widrow-Hoff Learning Objectives Theory and Examples ADALINE Network Single ADALINE Mean Square Error LMS Algorithm Analysis of Convergence Adaptive Filtering Adaptive Noise Cancellation Echo Cancellation Summary of Results Solved Problems Epilogue Further Reading Exercises 11. Backpropagation Objectives Theory and Examples Multilayer Perceptrons Pattern Classification ' Function Approximation The Backpropagation Algorithm Performance Index Chain Rule Backpropagating the Sensitivities Summary ' Example Using Backpropagation Choice of Network Architecture Convergence Generalization Summary of Results Solved Problems Epilogue Further Reading Exercises 12. Variations on Backpropagation Objectives Theory and Examples Drawbacks of Backpropagation Performance Surface Example Convergence Example Heuristic Modifications of Backpropagation Momentum Variable Learning Rate Numerical Optimization Techniques Conjugate Gradient Levenberg-Marquardt Algorithm Summary of Results Solved Problems Epilogue Further Reading Exercises 13. Assoeiative Learning Objectives Theory and Examples Simple Associative Network Unsupervised Hebb Rule Hebb Rule with Decay Simple Recognition Network Instar Rule Kohonen Rule Simple Recall Network Outstar Rule Summary of Results Solved Problems . Epilogue Further Reading Exercises 14. Competitive Networks Objectives Theory and Examples Hamming Network Layer 1 Layer 2 Competitive Layer Competitive Learning Problems with Competitive Layers Competitive Layers in Biology Self-Organizing Feature Maps Improving Feature Maps Learning Vector Quantization LVQ Learning Improving LVQ Networks (LVQ2) Summary of Results Solved Problems Epilogue Further Reading Exercises 15. Grossberg Network Objectives Theory and Examples Biological Motivation: Vision Illusions Vision Normalization Basic Nonlinear Model Two-Layer Competitive Network Layer 1 Layer 2 Choice of Transfer Function Learning Law Relation to Kohonen Law Summary of Results Solved Problems Epilogue Further Reading Exercises 16. Adaptive Resonance Theory Objectives Theory and Examples Overview of Adaptive Resonance Layer 1 Steady State Analysis ' Layer 2 Orienting Subsystem Learning Law: LI-L2 Subset/Superset Dilemma Learning Law Learning Law: L2-LI ARTI Algorithm Summary Initialization Algorithm Other ART Architectures Summary of Results Solved Problems Epilogue Further Reading Exercises 17. Stability Objectives Theory and Examples Recurrent Networks Stability Concepts Definitions Lyapunov Stability Theorem Pendulum Example LaSalle's Invariance Theorem Definitions Theorem Example Comments Summary of Results Solved Problems Epilogue Further Reading Exercises 18. Hopfield Network Objectives Theory and Examples Hopfield Model Lyapunov Function Invariant Sets Example Hopfield Attractors Effect of Gain Hopfield Design Content-Addressable Memory Hebb Rule Lyapunov Surface Summary of Results Solved Problems Epilogue Further Reading Exercises 19. Epilogue Objectives Theory and Examples Feedforward and Related Networks Competitive Networks Dynamic Associative Memory Networks Classical Foundations of Neural Networks Books and Journals Epilogue Further Reading
鄂公網(wǎng)安備 42010302001612號 