상세정보

Neural Network Learning and Expert Systems is the first book to present a unified and in-depth development of neural network learning algorithms and neural network expert systems. Especially suitable for students and researchers in computer science, engineering, and psychology, this text and reference provides a systematic development of neural network learning algorithms from a computational perspective, coupled with an extensive exploration of neural network expert systems which shows how the power of neural network learning can be harnessed to generate expert systems automatically.

Features include a comprehensive treatment of the standard learning algorithms (with many proofs), along with much original research on algorithms and expert systems. Additional chapters explore constructive algorithms, introduce computational learning theory, and focus on expert system applications to noisy and redundant problems.

For students there is a large collection of exercises, as well as a series of programming projects that lead to an extensive neural network software package. All of the neural network models examined can be implemented using standard programming languages on a microcomputer.

Stephen l. Gallant taught courses in neural network learning and expert systems as Associate Professor of Computer Science at Northeastern University. He is currently a Senior Scientist at HNC, Inc.

정보제공 :

CONTENTS
Foreword = xiii
Ⅰ Basics = 1
  1 Introduction and Important Definitions = 3
    1.1 Why Connectionist Models? = 3
    1.2 The Structure of Connectionist Models = 11
    1.3 Two Fundamental Models : Multilayer Perceptrons(MLP's) and Backpropagation Networks(BPN's) = 17
    1.4 Gradient Descent = 19
    1.5 Historic and Bibliographic Notes = 23
    1.6 Exercises = 27
    1.7 Programming Project = 29
  2 Representation Issues = 31
    2.1 Representing Boolean Functions = 31
    2.2 Distributed Representations = 39
    2.3 Feature Spaces and ISA Relations = 42
    2.4 Representing Real-Valued Functions = 48
    2.5 Example: Taxtime! = 55
    2.6 Exercises = 56
    2.7 Programming Projects = 59
Ⅱ Learning Single-Layer Models = 61
  3 Perceptron Learning and the Pocket Algorithm = 63
    3.1 Perceptron Learning for Separable Sets of Training Examples = 63
    3.2 The Pocket Algorithm for Nonseparable Sets of Training Examples = 74
    3.3 Khachiyan's Linear Programming Algorithm = 87
    3.4 Exercises = 88
    3.5 Programming Projects = 92
  4 Winner-Take-All Groups or Linear Machines = 95
    4.1 Generalizes Single-Cell Models = 96
    4.2 Perceptron Learning for Winner-Take-All Groups = 98
    4.3 The pcoket Algorithm for winner-Take-All Groups = 98
    4.4 Kessler's Construction, Perceptron Cycling, and the pocket Algorithm Proof = 99
    4.5 Independent Training = 102
    4.6 Exercises = 103
    4.7 programming Projects = 103
  5 Autoassociators and One-Shot Learning = 105
    5.1 Linear Autoassociators and the Outer-Product Training Rule = 105
    5.2 Anderson's BSB Model = 109
    5.3 Hopfield's Model = 110
    5.4 The Traveling Salesman Problem = 112
    5.5 The Cohen-Grossbeg Theorem = 115
    5.6 Kanerva's Model = 116
    5.7 Autoassociative Filtering for Feedforward Networks = 117
    5.8 Concluding Remarks = 118
    5.9 Exercises = 119
    5.10 Programming Projects = 121
  6 Mean Squared Error(MSE) Algorithm = 123
    6.1 Motivation = 123
    6.2 MSE Approximations = 123
    6.3 The Widrow-Hoff Rule or LMS Algorithm = 125
    6.4 ADALINE = 127
    6.5 Adaptive Noise Cancellation = 128
    6.6 Decision-Directed Learning = 129
    6.7 Exercises = 131
    6.8 Programming Projects = 131
  7 Unsupervised Learning = 133
    7.1 Introduction = 133
    7.2 k-Means clustering = 134
    7.3 Topology-Preserving Maps = 136
    7.4 ART1 = 143
    7.5 ART2 = 146
    7.6 Using Clustering Algorithms for Supervised Learning = 149
    7.7 Exercises = 150
    7.8 Programming Projects = 151
Ⅲ Learning in Multilayer Models = 153
  8 The Distributed Method and Radial Basis Functions= 155
    8.1 Rosenblatt's Approach = 156
    8.2 the Distributed Method = 157
    8.3 Exercises = 162
    8.4 How many Cells? = 163
    8.5 Radial Basis Functions = 165
    8.6 A Variant: The Anchor Algorithm = 167
    8.7 Scaling, Multipe outputs, and parallelism = 168
    8.8 Exercises = 170
    8.9 Programming Projects = 171
  9 Computational Learning theory and the BRD Algorithm = 173
    9.1 Introduction to Computational Learning theory = 173
    9.2 A Learning Algorithm for Probabilistic Bounded distributed Concepts = 178
    9.3 The BRD Theorem = 180
    9.4 Noisy Data and fallback Estimates = 183
    9.5 Bounds for Single-Layer Algorithms = 189
    9.6 Fitting Data by Limiting the Number of Iterations = 189
    9.7 Discussion = 191
    9.8 Exercises = 193
    9.9 Programming Projects = 193
  10 Constructive Algorithms = 195
    10.1 The Tower and Pyramid Algorithms = 195
    10.2 The Cascade-Correlation Algorithm = 198
    10.3 The Tiling Algorithm = 200
    10.4 The Upstart Algorithm = 201
    10.5 Other Constructive Algorithms and Pruning = 203
    10.6 easy Learning Problems = 205
    10.7 Exercises = 208
    10.8 Programming Projects = 209
  11 Backpropagation = 211
    11.1 The Backpropagation Algorithm = 212
    11.2 Derivation = 217
    11.3 Practical Considerations = 219
    11.4 NP-Completeness = 224
    11.5 Comments = 225
    11.6 Exercises = 227
    11.7 Programming Projects = 228
  12 Backpropagation: Variations and Applications = 231
    12.1 NETtalk = 231
    12.2 Backpropagation through Time = 233
    12.3 Handwritten Character Recognition = 235
    12.4 Robot Manipulator with Excess Degrees of Freedom = 239
    12.5 Exercises = 244
    12.6 Programming Projects = 244
  13 Simulated Annealing and Boltzmann Machines = 245
    13.1 Simulated Annealing = 245
    13.2 Boltzmann Machines = 246
    13.3 Remarks = 251
    13.4 Exercises = 251
    13.5 Programming Project = 251
Ⅳ Neural Network Expert Systems = 253
  14 Expert Systems and Neural Networks = 255
    14.1 Expert Systems = 255
    14.2 Neural Network Decision Systems = 264
    14.3 MACIE, and an Example Problem = 267
    14.4 Applicability of Neural Network Expert Systems = 281
    14.5 Exercise = 282
    14.6 Programming Projects = 282
  15 Details of the MACIE System = 283
    15.1 Inferencing and Forward Chaining = 283
    15.2 Confidence Estimation = 289
    15.3 Information Acquistion and Backward Chaining = 290
    15.4 Concluding Comment = 291
    15.5 Exercises = 291
    15.6 Programming Projects = 293
  16 Noise, Redundancy, Fault Detection, and Bayesian Decision Theory = 295
    16.1 The High Tech Lemonade Corporation's Problem = 295
    16.2 The Deep Model and the Noise Model = 298
    16.3 Generating the Expert System = 300
    16.4 Probabilistic Analysis = 302
    16.5 Noisy Single-Pattern Boolean Fault Detection Problems = 305
    16.6 Convergence Theorem = 308
    16.7 Comments = 310
    16.8 Exercises = 310
    16.9 Programming Projects = 311
  17 Extracting Rules from Networks = 315
    17.1 Why Rules? = 315
    17.2 What Kind of Rules? = 315
    17.3 Inference Justifications = 317
    17.4 Rule Sets = 322
    17.5 Conventional + Neural Network Expert Systems = 325
    17.6 Concluding Remarks = 328
    17.7 Exercises = 329
    17.8 Programming Projects = 329
Appendix : Representation Comparisons = 331
  A.1 DNF Expressions and Polynomial Representability = 331
  A.2 Decision Trees = 338
  A.3 π - λ Diagrams = 342
  A.4 Symmetric Functions and Depth Complexity = 343
  A.5 Concluding Remarks = 346
  A.6 Exercises = 346
Bibliography = 349
Index = 361