Neural and Adaptive Systems Fundamentals

Like no other text in this field, authors Jose C. Principe, Neil R. Euliano, and W. Curt Lefebvre have written a unique and innovative text unifying the concepts of neural networks and adaptive filters into a common framework. Included with the book is a CD-ROM that contains a hypertext version of the text seamlessly integrated with an interactive software simulator.

Jose C. Principe, University of Florida Neil R. Euliano and W. Curt Lefebvre, both of NeuroDimension, Inc.

Data Fitting With Linear Models

1

(67)

Introduction

2

(6)

Linear Models

8

(2)

Least Squares

10

(7)

Adaptive Linear Systems

17

(7)

Estimation of the Gradient: the LMS Algorithm

24

(7)

A Methodology for Stable Adaptation

31

(10)

Regression for Multiple Variables

41

(15)

Newton's Method

56

(3)

Analytic versus Iterative Solutions

59

(1)

The Linear Regression Model

59

(4)

Conclusions

63

(1)

Exercises

64

(1)

NeuroSolutions Examples

65

(1)

Concept Map for Chapter 1

66

(2)

References

67

(1)

Pattern Recognition

68

(32)

The Pattern-Recognition Problem

68

(3)

Statistical Formulation of Classifiers

71

(17)

Linear and Nonlinear Classifier Machines

88

(6)

Methods of Training Parametric Classifiers

94

(3)

Conclusions

97

(1)

Exercises

97

(1)

NeuroSolutions Example

98

(1)

Concept Map for Chapter 2

98

(2)

References

99

(1)

Multilayer Perceptrons

100

(73)

Artificial Neural Networks (ANNs)

101

(1)

Pattern-Recognition Ability of the McCulloch-Pitts PE

102

(20)

The Perceptron

122

(10)

One-Hidden-Layer Multilayer Perceptrons

132

(12)

MLPs With Two Hidden Layers

144

(5)

Training Static Networks with the Backpropagation Procedure

149

(11)

Training Embedded Adaptive Systems

160

(3)

MLPs as Optimal Classifiers

163

(4)

Conclusions

167

(1)

NeuroSolutions Examples

167

(1)

Exercises

168

(3)

Concept Map for Chapter 3

171

(2)

References

172

(1)

Designing and Training MLPS

173

(50)

Introduction

174

(1)

Controlling Learning in Practice

174

(10)

Other Search Procedures

184

(11)

Stop Criteria

195

(3)

How Good Are MLPs as Learning Machines?

198

(4)

Error Criterion

202

(6)

Network Size and Generalization

208

(5)

Project: Application of the MLP to Real-World Data

213

(5)

Conclusion

218

(1)

List of NeuroSolutions Examples

219

(1)

Exercises

219

(2)

Concept Map for Chapter 4

221

(2)

References

222

(1)

Function Approximation With MLPS, Radial Basis Functions, and Support Vector Machines

223

(56)

Introduction

224

(2)

Function Approximation

226

(3)

Choices for the Elementary Functions

229

(15)

Probablistic Interpretation of the Mappings: Nonlinear Regression

244

(1)

Training Neural Networks for function Approximation

245

(4)

How to Select the Number of Bases

249

(8)

Applications of Radial Basis Functions

257

(4)

Support Vector Machines

261

(8)

Project: Applications of Neural Networks as Function Approximators

269

(5)

Conclusion

274

(1)

Exercises

274

(1)

NeuroSolutions Examples

275

(2)

Concept Map for Chapter 5

277

(2)

References

278

(1)

Hebbian Learning and Principal Component Analysis

279

(54)

Introduction

280

(1)

Effect of the Hebbian Update

281

(11)

Oja's Rule

292

(4)

Principal Component Analysis

296

(8)

Anti-Hebbian Learning

304

(2)

Estimating Cross-Correlation with Hebbian Networks

306

(3)

Novelty Filters and Lateral Inhibition

309

(3)

Linear Associative Memories (LAMs)

312

(4)

LMS Learning as a Combination of Hebbian Rules

316

(3)

Autoassociation

319

(5)

Nonlinear Associative Memories

324

(1)

Project: Use of Hebbian Networks for Data Compression and Associative Memories

325

(2)

Conclusions

327

(1)

Exercises

328

(1)

NeuroSolutions Examples

329

(2)

Concept Map for Chapter 6

331

(2)

References

332

(1)

Competitive and Kohonen Networks

333

(31)

Introduction

334

(1)

Competition and Winner-Take-All Networks

335

(2)

Competitive Learning

337

(4)

Clustering

341

(3)

Improving Competitive Learning

344

(3)

Soft Competition

347

(1)

Kohonen Self-Organizing Map

348

(6)

Creating Classifiers from Competitive Networks

354

(3)

Adaptive Resonance Theory (ART)

357

(1)

Modular Networks

358

(2)

Conclusions

360

(1)

Exercises

360

(1)

NeuroSolutions Examples

361

(1)

Concept Map for Chapter 7

362

(2)

References

363

(1)

Principles of Digital Signal Processing

364

(65)

Time Series and Computers

365

(4)

Vectors and Discrete Signals

369

(7)

The Concept of Filtering

376

(6)

Time Domain Analysis of Linear Systems

382

(6)

Recurrent Systems and Stability

388

(4)

Frequency Domain Analysis

392

(12)

The Z Transform and the System Transfer Function

404

(3)

The Frequency Response

407

(3)

Frequency Response and Poles and Zeros

410

(5)

Types of Linear Filters

415

(3)

Project: Design of Digital Filters

418

(5)

Conclusions

423

(1)

Exercises

424

(1)

NeuroSolutions Examples

425

(2)

Concept Map for Chapter 8

427

(2)

References

428

(1)

Adaptive Filters

429

(44)

Introduction

430

(1)

The Adaptive Linear Combiner and Linear Regression

430

(1)

Optimal Filter Weights

431

(8)

Properties of the Iterative Solution

439

(3)

Hebbian Networks for Time Processing

442

(3)

Applications of the Adaptive Linear Combiner

445

(18)

Applications of Temporal PCA Networks

463

(6)

Conclusions

469

(1)

Exercises

469

(1)

NeuroSolutions Examples

470

(1)

Concept Map for Chapter 9

471

(2)

References

472

(1)

Temporal Processing with Neural Networks

473

(52)

Static versus Dynamic Systems

474

(3)

Extracting Information in Time

477

(2)

The Focused Time-Delay Neural Network (TDNN)

479

(6)

The Memory PE

485

(6)

The Memory Filter

491

(4)

Design of the Memory Space

495

(2)

The Gamma Memory PE

497

(5)

Time-Lagged Feedforward Networks

502

(13)

Focused TLFNs Built From RBFs

515

(3)

Project: Iterative Prediction of Chaotic Time Series

518

(2)

Conclusions

520

(1)

Exercises

520

(1)

NeuroSolutions Examples

521

(2)

Concept Map for Chapter 10

523

(2)

References

524

(1)

Training and Using Recurrent Networks

525

(64)

Introduction

526

(1)

Simple Recurrent Topologies

527

(2)

Adapting the Feedback Parameter

529

(2)

Unfolding Recurrent Networks in Time

531

(13)

The Distributed TLFN Topology

544

(6)

Dynamic Systems

550

(3)

Recurrent Neural Networks

553

(3)

Learning Paradigms for Recurrent Systems

556

(5)

Applications of Dynamic Networks to System Identification and Control

561

(6)

Hopfield Networks

567

(7)

Grossberg's Additive Model

574

(3)

Beyond First-Order Dynamics: Freeman's Model

577

(6)

Conclusions

583

(1)

Exercises

583

(2)

NeuroSolutions Examples

585

(1)

Concept Map for Chapter 11

586

(3)

References

587

(2)

APPENDIX A ELEMENTS OF LINEAR ALGEBRA AND PATTERN RECOGNITION

589

(24)

A.1 Introduction

589

(1)

A.2 Vectors: Concepts and Definitions

590

(6)

A.3 Matrices: Concepts and Definitions

596

(6)

A.4 Random Vectors

602

(9)

A.5 Conclusions

611

(2)

APPENDIX B NEUROSOLUTIONS TUTORIAL

613

(24)

B.1 Introduction to Neurosolutions

613

(1)

B.2 Introduction to the Interactive Examples

614

(2)

B.3 Basic Operation of Neurosolutions

616

(7)

B.4 Probing the System

623

(4)

B.5 The Input Family

627

(5)

B.6 Training a Network

632

(3)

B.7 Summary

635

(2)

APPENDIX C DATA DIRECTORY

637

(2)

Glossary

639

(8)

Index

647

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Neural and Adaptive Systems Fundamentals through Simulations

Summary

Author Biography

Table of Contents

Supplemental Materials

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Neural and Adaptive Systems Fundamentals through Simulations

Summary

Author Biography

Table of Contents

Supplemental Materials

Digital License