Structure Level Adaptation for Artificial Neural Networks (The Springer International Series in Engineering and Computer Science, 133)

Tsu-Chang Lee

ISBN 10: 1461367654 / ISBN 13: 9781461367659

Editore: Springer, 2012

Riguardo questo articolo

Like New.

Codice articolo ERICA80014613676546

Dati bibliografici

• Titolo: Structure Level Adaptation for Artificial Neural Networks (The Springer International Series in Engineering and Computer Science, 133)
• Editore: Springer
• Data di pubblicazione: 2012
• Lingua: Inglese
• ISBN 10: 1461367654
• ISBN 13: 9781461367659
• Rilegatura: Paperback
• Condizione: Like New
• Tipo di libro: book

Descrizione articolo

Riassunto

63 3. 2 Function Level Adaptation 64 3. 3 Parameter Level Adaptation. 67 3. 4 Structure Level Adaptation 70 3. 4. 1 Neuron Generation . 70 3. 4. 2 Neuron Annihilation 72 3. 5 Implementation . . . . . 74 3. 6 An Illustrative Example 77 3. 7 Summary . . . . . . . . 79 4 Competitive Signal Clustering Networks 93 4. 1 Introduction. . 93 4. 2 Basic Structure 94 4. 3 Function Level Adaptation 96 4. 4 Parameter Level Adaptation . 101 4. 5 Structure Level Adaptation 104 4. 5. 1 Neuron Generation Process 107 4. 5. 2 Neuron Annihilation and Coalition Process 114 4. 5. 3 Structural Relation Adjustment. 116 4. 6 Implementation . . 119 4. 7 Simulation Results 122 4. 8 Summary . . . . . 134 5 Application Example: An Adaptive Neural Network Source Coder 135 5. 1 Introduction. . . . . . . . . . 135 5. 2 Vector Quantization Problem 136 5. 3 VQ Using Neural Network Paradigms 139 Vlll 5. 3. 1 Basic Properties . 140 5. 3. 2 Fast Codebook Search Procedure 141 5. 3. 3 Path Coding Method. . . . . . . 143 5. 3. 4 Performance Comparison . . . . 144 5. 3. 5 Adaptive SPAN Coder/Decoder 147 5. 4 Summary . . . . . . . . . . . . . . . . . 152 6 Conclusions 155 6. 1 Contributions 155 6. 2 Recommendations 157 A Mathematical Background 159 A. 1 Kolmogorov's Theorem . 160 A. 2 Networks with One Hidden Layer are Sufficient 161 B Fluctuated Distortion Measure 163 B. 1 Measure Construction . 163 B. 2 The Relation Between Fluctuation and Error 166 C SPAN Convergence Theory 171 C. 1 Asymptotic Value of Wi 172 C. 2 Energy Function . .

Contenuti

1 Introduction.- 1.1 Background.- 1.2 Neural Network Paradigms.- 1.3 The Frame Problem in Artificial Neural Networks.- 1.4 Approach.- 1.5 Overview of This Book.- 2 Basic Framework.- 2.1 Introduction.- 2.2 Formal Neurons.- 2.3 Formal Neural Networks.- 2.4 Multi-Level Adaptation Formalism.- 2.5 Activity-Based Structural Adaptation.- 2.5.1 Neuron generation.- 2.5.2 Neuron Annihilation.- 2.5.3 Structural Relationship Modification.- 2.6 Summary.- 3 Multi-Layer Feed-Forward Networks.- 3.1 Introduction.- 3.2 Function Level Adaptation.- 3.3 Parameter Level Adaptation.- 3.4 Structure Level Adaptation.- 3.4.1 Neuron Generation.- 3.4.2 Neuron Annihilation.- 3.5 Implementation.- 3.6 An Illustrative Example.- 3.7 Summary.- 4 Competitive Signal Clustering Networks.- 4.1 Introduction.- 4.2 Basic Structure.- 4.3 Function Level Adaptation.- 4.4 Parameter Level Adaptation.- 4.5 Structure Level Adaptation.- 4.5.1 Neuron Generation Process.- 4.5.2 Neuron Annihilation and Coalition Process.- 4.5.3 Structural Relation Adjustment.- 4.6 Implementation.- 4.7 Simulation Results.- 4.8 Summary.- 5 Application Example: An Adaptive Neural Network Source Coder.- 5.1 Introduction.- 5.2 Vector Quantization Problem.- 5.3 VQ Using Neural Network Paradigms.- 5.3.1 Basic Properties.- 5.3.2 Fast Codebook Search Procedure.- 5.3.3 Path Coding Method.- 5.3.4 Performance Comparison.- 5.3.5 Adaptive SPAN Coder/Decoder.- 5.4 Summary.- 6 Conclusions.- 6.1 Contributions.- 6.2 Recommendations.