Table of Contents
Acknowledgements vii
Preface ix
Chapter 1 Deep Learning Neural Networks: Methodology and Scope 1
1.1 Definition 1
1.2 Brief History of DNN and of its Applications 2
1.3 The Scope of the Present Text 5
1.4 Brief Outline 7
References 9
Chapter 2 Basic Concepts of Neural Networks 13
2.1 The Hebbian Principle 13
2.2 The Perception 14
2.3 Associative Memory 16
2.4 Winner-Takes-All Principle 18
2.5 The Convolution Integral 18
References 20
Chapter 3 Back-Propagation 23
3.1 The Back Propagation Architecture 23
3.2 Derivation of the BP Algorithm 24
3.3 Modified BP Algorithms 29
References 31
Chapter 4 The Cognitron and Neocognitron 33
4.1 Introduction 33
4.2 Principles of the Cognitron 33
4.3 Network Operation 34
4.4 Cognitron Training 36
4.5 The Neocognitron 37
References 39
Chapter 5 Deep Learning Convolutional Neural Networks 41
5.1 Introduction 41
5.2 CNN Structure 42
5.3 The Convolutional Layers 46
5.4 Back Propagation 47
5.5 RELU Layers 48
5.6 Pooling Layers 49
5.7 Dropout 50
5.8 Output FC Layer 51
5.9 Parameter (Weight) Sharing 00
5.10 Applications 52
5.11 Case Studies (with program codes) 53
References 53
Chapter 6 LAMSTAR-1 and LAMSTAR-2 Neural Networks 57
6.1 LAMSTAR Principles 57
6.2 LAMSTAR-1 (LNN-l) 71
6.3 LAMSTAR-2 (LNN-2) 77
6.4 Data Analysis with LAMSTAR-1 and LAMSTAR-2 85
6.5 LAMSTAR Data-Balancing Pre-Setting Procedure 90
6.6 Comments and Applications 95
References 98
Chapter 7 Other Neural Networks for Deep Learning 101
7.1 Deep Boltzmann Machines (DBM) 101
7.2 Deep Recurrent Learning Neural Networks (DRN) 104
7.3 Deconvolution/Wavelet Neural Networks 104
References 108
Chapter 8 Case Studies 111
8.1 Human Activities Recognition A Bose 111
8.2 Medicine: Predicting Onset of Seizures in Epilepsy J Tran 116
8.3 Medicine: Image Processing: Cancer Detection D Bose 117
8.4 Image Processing: From 2D Images to 3D J C Somasundaram 119
8.5 Image Analysis: Scene Classification N Koundinya 120
8.6 Image Recognition: Fingerprint Recognition 1 A Daggubati 122
8.7 Image Recognition: Fingerprint Recognition 2 A Ponguru 124
8.8 Face Recognition S Gangineni 125
8.9 Image Recognition - Butterfly Species Classification V N S Kadi 126
8.10 Image Recognition: Leaf Classification P Bondili 127
8.11 Image Recognition: Traffic Sign Recognition D Somasundaram 129
8.12 Information Retrieval: Programming Language Classification E Wolfson 130
8.13 Information Retrieval: Data Classification from Transcribed Spoken Conversation A Kumar 131
8.14 Speech Recognition M Racha 133
8.15 Music Genre Classification Y Fan C Deshpande 134
8.16 Security/Finance: Credit Card Fraud Detection F Wang 135
8.17 Predicting Location for Oil Drilling from Permeability Data in Test Drills A S Hussain 136
8.18 Prediction of Forest Fires S R K Muralidharan 138
8.19 Predicting Price Movement in Market Microstructure X Shi 139
8.20 Fault Detection: Bearing Fault Diagnosis via Acoustic Emission M He 140
Chapter 9 Concluding Comments 141
Problems 147
Appendices to Case Studies of Chapter 8 153
A.8.1 Human Activity - Codes A Bose 154
A.8.2 Predicting Seizures in Epilepsy J Tran 161
A.8.3 Cancer Detection D Bose 167
A.8.4 Depth Information from 2D Images J C Somaundaram 171
A.8.5 Scene Classification N Koudinya 176
A.8.6 Fingerprint Recognition 1 A Daggubati 181
A.8.7 Fingerprint Recognition 2 A Ponguru 182
A.8.8 Face Recognotion S Gangineni 183
A.8.9 Butterfly Species Recognition V R S S Kadi 188
A.8.10 Leaf Classification P Bondili 198
A.8.11 Traffic Sign Recognition D Somasundaram 200
A.8.12 Programming-Language Classification E Wolfson 201
A.8.13 Data Classification from Transcribed Spoken Text A Kumar 207
A.8.14 Speech Recognition M Racha 225
A.8.15 Music Genre Classification C Deshpande 232
A.8.16 Credit Card Fraud Detection F Wang 237
A.8.17 Predicting Site for Oil Drilling from Permeability Data S A Hussain 240
A.8.18 Predicting Forest Fires S R K Muralidharan 244
A.8.19 Predicting Price Movement in Market Microstructure X Shi 250
A.8.20 Fault Detection M He 250
Author Index 255
Subject Index 259
