Sold Out
Book Categories |
Preface V
Introduction 1
Background 1
Neuron Model 2
Historical Remarks 4
Network architecture 6
Supervised Neural Networks 6
McCulloh and Pitts Model 7
The Perceptron Model 11
Multi-layer Feedforward Network 14
Recurrent Networks 15
Unsupervised Neural Networks 17
Modeling and Learning Mechanism 19
Determination of Parameters 20
Gradient Descent Searching Method 26
Exercises 28
Learning Performance and Enhancement 31
Fundamental of Gradient Descent Optimization 32
Conventional Backpropagation Algorithm 35
Convergence Enhancement 42
Extended Backpropagation Algorithm 44
Least Squares Based Training Algorithm 47
Extended Least Squares Based Algorithm 55
Initialization Consideration 59
Weight Initialization Algorithm I 61
Weight Initialization Algorithm II 64
Weight Initialization Algorithm III 67
Global Learning Algorithms 69
Simulated Annealing Algorithm 70
Alopex Algorithm 71
Reactive Tabu Search 72
The NOVEL Algorithm 73
The Heuristic Hybrid Global Learning Algorithm 74
Concluding Remarks 82
Fast Learning Algorithms 82
Weight Initialization Methods 83
Global Learning Algorithms 84
Appendix 2.1 85
Exercises 87
Generalization and Performance Enhancement 91
Cost Function and Performance Surface 93
Maximum Likelihood Estimation 94
The Least-Square Cost Function 95
Higher-Order Statistic Generalization 98
Definitions and Properties of Higher-Order Statistics 99
The Higher-Order Cumulants based Cost Function 101
Property of the Higher-Order Cumulant Cost Function 105
Learning and Generalization Performance 108
Experiment one: Henon Attractor 109
Experiment Two: Sunspot time-series 116
Regularization for Generalization Enhancement 117
Adaptive Regularization Parameter Selection (ARPS) Method 120
Stalling Identification Method 121
[lambda] Selection Schemes 122
Synthetic Function Mapping 124
Concluding Remarks 126
Objective function selection 128
Regularization selection 129
Confidence Upper Bound of Approximation Error 131
Proof of the Property of the HOC Cost Function 133
The Derivation of the Sufficient Conditions of the Regularization Parameter 136
Exercises 137
Basis Function Networks for Classification 139
Linear Separation and Perceptions 140
Basis Function Model for Parametric Smoothing 142
Radial Basis Function Network 144
RBF Networks Architecture 144
Universal Approximation 146
Initialization and Clustering 149
Learning Algorithms 152
Linear Weights Optimization 152
Gradient Descent Optimization 154
Hybrid of Least Squares and Penalized Optimization 155
Regularization Networks 157
Advanced Radial Basis Function Networks 159
Support Vector Machine 159
Wavelet Network 161
Fuzzy RBF Controllers 164
Probabilistic Neural Networks 167
Concluding Remarks 169
Exercises 170
Self-organizing Maps 173
Introduction 173
Self-Organizing Maps 177
Learning Algorithm 178
Growing SOMs 182
Cell Splitting Grid 182
Growing Hierarchical Self-Organizing Quadtree Map 185
Probabilistic SOMs 188
Cellular Probabilistic SOM 188
Probabilistic Regularized SOM 193
Clustering of SOM 202
Multi-Layer SOM for Tree-Structured data 205
SOM Input Representation 207
MLSOM Training 210
MLSOM visualization and classification 212
Exercises 216
Classification and Feature Selection 219
Introduction 219
Support Vector Machines (SVM) 223
Support Vector Machine Visualization (SVMV) 224
Cost Function 229
MSE and MCE Cost Functions 230
Hybrid MCE-MSE Cost Function 232
Implementing MCE-MSE 236
Feature Selection 239
Information Theory 241
Mutual Information 241
Probability density function (pdf) estimation 243
MI Based Forward Feature Selection 245
MIFS and MIFS-U 247
Using quadratic MI 248
Exercises 253
Engineering Applications 255
Electric Load Forecasting 255
Nonlinear Autoregressive Integrated Neural Network Model 257
Case Studies 261
Content-based Image Retrieval Using SOM 266
GHSOQM Based CBIR Systems 267
Overall Architecture of GHSOQM-Based CBIR System 267
Image Segmentation, Feature Extraction and Region-Based Feature Matrices 268
Image Distance 269
GHSOQM and Relevance Feedback in the CBIR System 270
Performance Evaluation 274
Feature Selection for cDNA Microarray 278
MI Based Forward Feature Selection Scheme 279
The Supervised Grid Based Redundancy Elimination 280
The Forward Gene Selection Process Using MIIO and MISF 281
Results 282
Prostate Cancer Classification Dataset 284
Subtype of ALL Classification Dataset 288
Remarks 294
Bibliography 291
Index 305
Login|Complaints|Blog|Games|Digital Media|Souls|Obituary|Contact Us|FAQ
CAN'T FIND WHAT YOU'RE LOOKING FOR? CLICK HERE!!! X
You must be logged in to add to WishlistX
This item is in your Wish ListX
This item is in your CollectionNeural Networks and Computing: Learning Algorithms and Applications, Vol. 7
X
This Item is in Your InventoryNeural Networks and Computing: Learning Algorithms and Applications, Vol. 7
X
You must be logged in to review the productsX
X
X
Add Neural Networks and Computing: Learning Algorithms and Applications, Vol. 7, This book covers neural networks with special emphasis on advanced learning methodologies and applications. It includes practical issues of weight initializations, stalling of learning, and escape from a local minima, which have not been covered by many e, Neural Networks and Computing: Learning Algorithms and Applications, Vol. 7 to the inventory that you are selling on WonderClubX
X
Add Neural Networks and Computing: Learning Algorithms and Applications, Vol. 7, This book covers neural networks with special emphasis on advanced learning methodologies and applications. It includes practical issues of weight initializations, stalling of learning, and escape from a local minima, which have not been covered by many e, Neural Networks and Computing: Learning Algorithms and Applications, Vol. 7 to your collection on WonderClub |