Amazon no longer offers textbook rentals. We do!

Neural Networks : A Comprehensive Foundation

by: Haykin, Simon

Neural Networks : A Comprehensive Foundation

by: Haykin, Simon

ISBN 13:
9780132733502
ISBN 10:
0132733501
Edition: 2nd
Format: Hardcover
Copyright: 01/01/2009
Publisher: Prentice Hall
Newer Edition

Rent

Sorry, this item is currently unavailable.

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

Extend or Purchase Your Rental at Any Time

Need to keep your rental past your due date? At any time before your due date you can extend or purchase your rental through your account.

Summary

For graduate-level neural network courses offered in the departments of Computer Engineering, Electrical Engineering, and Computer Science.Renowned for its thoroughness and readability, this well-organized and completely up-to-date text remains the most comprehensive treatment of neural networks from an engineering perspective. Thoroughly revised.

Preface

xii

Acknowledgments

Abbreviations and Symbols

xvii

Introduction

(49)

What Is a Neural Network?

(5)

Human Brain

(4)

Models of a Neuron

(5)

Neural Networks Viewed as Directed Graphs

(3)

Feedback

(3)

Network Architectures

(2)

Knowledge Representation

(11)

Artificial Intelligence and Neural Networks

(4)

Historical Notes

(12)

Notes and References

(1)

Problems

(5)

Learning Processes

(67)

Introduction

(1)

Error-Correction Learning

(2)

Memory-Based Learning

(2)

Hebbian Learning

(3)

Competitive Learning

(2)

Boltzmann Learning

(2)

Credit Assignment Problem

(1)

Learning with a Teacher

(1)

Learning without a Teacher

(2)

Learning Tasks

(9)

Memory

(8)

Adaptation

(1)

Statistical Nature of the Learning Process

(5)

Statistical Learning Theory

(13)

Probably Approximately Correct Model of Learning

102

(3)

Summary and Discussion

105

(12)

Notes and References

106

(5)

Problems

111

(6)

Single Layer Perceptrons

117

(39)

Introduction

117

(1)

Adaptive Filtering Problem

118

(3)

Unconstrained Optimization Techniques

121

(5)

Linear Least-Squares Filters

126

(2)

Least-Mean-Square Algorithm

128

(5)

Learning Curves

133

(1)

Learning Rate Annealing Techniques

134

(1)

Perceptron

135

(2)

Perceptron Convergence Theorem

137

(6)

Relation Between the Perceptron and Bayes Classifier for a Gaussian Environment

143

(5)

Summary and Discussion

148

(8)

Notes and References

150

(1)

Problems

151

(5)

Multilayer Perceptrons

156

(100)

Introduction

156

(3)

Some Preliminaries

159

(2)

Back-Propagation Algorithm

161

(12)

Summary of the Back-Propagation Algorithm

173

(2)

XOR Problem

175

(3)

Heuristics for Making the Back-Propagation Algorithm Perform Better

178

(6)

Output Representation and Decision Rule

184

(3)

Computer Experiment

187

(12)

Feature Detection

199

(3)

Back-Propagation and Differentiation

202

(2)

Hessian Matrix

204

(1)

Generalization

205

(3)

Approximations of Functions

208

(5)

Cross-Validation

213

(5)

Network Pruning Techniques

218

(8)

Virtues and Limitations of Back-Propagation Learning

226

(7)

Accelerated Convergence of Back-Propagation Learning

233

(1)

Supervised Learning Viewed as an Optimization Problem

234

(11)

Convolutional Networks

245

(2)

Summary and Discussion

247

(9)

Notes and References

248

(4)

Problems

252

(4)

Radial-Basis Function Networks

256

(62)

Introduction

256

(1)

Cover's Theorem on the Separability of Patterns

257

(5)

Interpolation Problem

262

(3)

Supervised Learning as an Ill-Posed Hypersurface Reconstruction Problem

265

(2)

Regularization Theory

267

(10)

Regularization Networks

277

(1)

Generalized Radial-Basis Function Networks

278

(4)

XOR Problem (Revisited)

282

(2)

Estimation of the Regularization Parameter

284

(6)

Approximation Properties of RBF Networks

290

(3)

Comparison of RBF Networks and Multilayer Perceptrons

293

(1)

Kernel Regression and Its Its Relation to RBF Networks

294

(4)

Learning Strategies

298

(7)

Computer Experiment

305

(3)

Summary and Discussion

308

(10)

Notes and References

308

(4)

Problems

312

(6)

Support Vector Machines

318

(33)

Introduction

318

(1)

Optimal Hyperplane for Linearly Separable Patterns

319

(7)

Optimal Hyperplane for Nonseparable Patterns

326

(3)

How to Build a Support Vector Machine for Pattern Recognition

329

(6)

Example: XOR Problem (Revisited)

335

(2)

Computer Experiment

337

(2)

&epsis;-Insensitive Loss Function

339

(1)

Support Vector Machines for Nonlinear Regression

340

(3)

Summary and Discussion

343

(8)

Notes and References

347

(1)

Problems

348

(3)

Committee Machines

351

(41)

Introduction

351

(2)

Ensemble Averaging

353

(2)

Computer Experiment I

355

(2)

Boosting

357

(7)

Computer Experiment II

364

(2)

Associative Gaussian Mixture Model

366

(6)

Hierarchical Mixture of Experts Model

372

(2)

Model Selection Using a Standard Decision Tree

374

(3)

A Priori and A Posteriori Probabilities

377

(1)

Maximum Likelihood Estimation

378

(2)

Learning Strategies for the HME Model

380

(2)

EM Algorithm

382

(1)

Application of the EM Algorithm to the HME Model

383

(3)

Summary and Discussion

386

(6)

Notes and References

387

(2)

Problems

389

(3)

Principal Components Analysis

392

(51)

Introduction

392

(1)

Some Intuitive Principles of Self-Organization

393

(3)

Principal Components Analysis

396

(8)

Hebbian-Based Maximum Eigenfilter

404

(9)

Hebbian-Based Principal Components Analysis

413

(6)

Computer Experiment: Image Coding

419

(3)

Adaptive Principal Components Analysis Using Lateral Inhibition

422

(8)

Two Classes of PCA Algorithms

430

(1)

Batch and Adaptive Methods of Computation

430

(2)

Kernel-Based Principal Components Analysis

432

(5)

Summary And Discussion

437

(6)

Notes And References

439

(1)

Problems

440

(3)

Self-Organizing Maps

443

(41)

Introduction

443

(1)

Two Basic Feature-Mapping Models

444

(2)

Self-Organizing Map

446

(7)

Summary of the SOM Algorithm

453

(1)

Properties of the Feature Map

454

(7)

Computer Simulations

461

(5)

Learning Vector Quantization

466

(2)

Computer Experiment: Adaptive Pattern Classification

468

(2)

Hierarchical Vector Quantization

470

(4)

Contextual Maps

474

(2)

Summary and Discussion

476

(8)

Notes and References

477

(2)

Problems

479

(5)

Information-Theoretic Models

484

(61)

Introduction

484

(1)

Entropy

485

(5)

Maximum Entropy Principle

490

(2)

Mutual Information

492

(3)

Kullback-Leibler Divergence

495

(3)

Mutual Information as an Objective Function To Be Optimized

498

(1)

Maximum Mutual Information Principle

499

(4)

Infomax and Redundancy Reduction

503

(3)

Spatially Coherent Features

506

(2)

Spatially Incoherent Features

508

(2)

Independent Components Analysis

510

(13)

Computer Experiment

523

(2)

Maximum Likelihood Estimation

525

(4)

Maximum Entropy Method

529

(4)

Summary and Discussion

533

(12)

Notes and References

535

(6)

Problems

541

(4)

Stochastic Machines And Their Approximates Rooted in Statistical Mechanics

545

(58)

Introduction

545

(1)

Statistical Mechanics

546

(2)

Markov Chains

548

(8)

Metropolis Algorithm

556

(2)

Simulated Annealing

558

(3)

Gibbs Sampling

561

(1)

Boltzmann Machine

562

(7)

Sigmoid Belief Networks

569

(5)

Helmholtz Machine

574

(2)

Mean-Field Theory

576

(2)

Deterministic Boltzmann Machine

578

(1)

Deterministic Sigmoid Belief Networks

579

(7)

Deterministic Annealing

586

(6)

Summary and Discussion

592

(11)

Notes and References

594

(3)

Problems

597

(6)

Neurodynamic Programming

603

(32)

Introduction

603

(1)

Markovian Decision Processes

604

(3)

Bellman's Optimality Criterion

607

(3)

Policy Iteration

610

(2)

Value Iteration

612

(5)

Neurodynamic Programming

617

(1)

Approximate Policy Iteration

618

(4)

Q-Learning

622

(5)

Computer Experiment

627

(2)

Summary and Discussion

629

(6)

Notes and References

631

(1)

Problems

632

(3)

Temporal Processing Using Feedforward Networks

635

(29)

Introduction

635

(1)

Short-term Memory Structures

636

(4)

Network Architectures for Temporal Processing

640

(3)

Focused Time Lagged Feedforward Networks

643

(2)

Computer Experiment

645

(1)

Universal Myopic Mapping Theorem

646

(2)

Spatio-Temporal Models of a Neuron

648

(3)

Distributed Time Lagged Feedforward Networks

651

(1)

Temporal Back-Propagation Algorithm

652

(7)

Summary and Discussion

659

(5)

Notes and References

660

(1)

Problems

660

(4)

Neurodynamics

664

(68)

Introduction

664

(2)

Dynamical Systems

666

(3)

Stability of Equilibrium States

669

(5)

Attractors

674

(2)

Neurodynamical Models

676

(4)

Manipulation of Attractors as a Recurrent Network Paradigm

680

(1)

Hopfield Models

680

(16)

Computer Experiment I

696

(5)

Cohen-Grossberg Theorem

701

(2)

Brain-State-in-a-Box Model

703

(6)

Computer Experiment II

709

(1)

Strange Attracotrs and Chaos

709

(5)

Dynamic Reconstruction of a Chaotic Process

714

(4)

Computer Experiment III

718

(4)

Summary and Discussion

722

(10)

Notes and References

725

(2)

Problems

727

(5)

Dynamically Driven Recurrent Networks

732

(58)

Introduction

732

(1)

Recurrent Network Architectures

733

(6)

State-Space Model

739

(7)

Nonlinear Autoregressive with Exogenous Inputs Model

746

(1)

Computation Power of Recurrent Networks

747

(3)

Learning Algorithms

750

(1)

Back-Propagation Through Time

751

(5)

Real-Time Recurrent Learning

756

(6)

Kalman Filters

762

(3)

Decoupled Extended Kalman Filters

765

(5)

Computer Experiment

770

(3)

Vanishing Gradients in Recurrent Networks

773

(3)

System Identification

776

(4)

Model-Reference Adaptive Control

780

(2)

Summary and Discussion

782

(8)

Notes and References

783

(2)

Problems

785

(5)

Epilogue

790

(6)

Bibliography

796

(41)

Index

837

Amazon no longer offers textbook rentals. We do!

Neural Networks : A Comprehensive Foundation

Neural Networks : A Comprehensive Foundation

9780132733502

0132733501

Summary

Table of Contents

Supplemental Materials

Write a Review

Amazon no longer offers textbook rentals. We do!

Neural Networks : A Comprehensive Foundation

Neural Networks : A Comprehensive Foundation

9780132733502

0132733501

Summary

Table of Contents

Supplemental Materials

Write a Review

Related Products