상세정보

Neural Network Modeling offers a cohesive approach to the statistical mechanics and principles of cybernetics as a basis for neural network modeling. It brings together neurobiologists and the engineers who design intelligent automata to understand the physics of collective behavior pertinent to neural elements and the self-control aspects of neurocybernetics. The theoretical perspectives and explanatory projections portray the most current information in the field, some of which counters certain conventional concepts in the visualization of neuronal interactions.

Neural Network Modeling offers a cohesive approach to the statistical mechanics and principles of cybernetics as a basis for neural network modeling

정보제공 :

CONTENTS
Chapter 1 : Introduction
 1.1 General = 1
 1.2 Stochastical Aspects and Physics of Neural Activity = 2
 1.3 Neurocy bernetic Concepts = 5
 1.4 Statistical Mechanics-Cybernetics-Neural Complex = 11
 1.5 Concluding Remarks = 14
Chapter 2 : Neural and Brain Complex
 2.1 Introduction = 15
 2.2 Gross Features of the Brain and the Nervous System = 17
 2.3 Neurons and Their Characteristics = 18
 2.4 Biochemical and Electrical Activities in Neurons = 20
 2.5 Mode(s) of Communication among Neurons = 22
 2.6 Collective Response of Neurons = 25
 2.7 Neural Net : A Self-Organizing Finite Automaton = 30
 2.8 Concluding Remarks = 30
Chapter 3 : Concepts of Mathematical Neurobiology
 3.1 Mathematical Neurobiology : Past and Present = 31
 3.2 Mathematics of Neural Activities = 35
 3.3 Models of Memory in Neural Networks = 40
 3.4 Net Function and Neuron Function = 42
 3.5 Concluding Remarks = 43
Chapter 4 : Pseudo-Thermodynamics of Neural Activity
 4.1 Introduction = 44
 4.2 Machine Representation of Neural Network = 47
 4.3 Neural Network versus Machine Concepts = 49
 4.4 Simulated Annealing and Energy Function = 54
 4.5 Cooling Schedules = 55
 4.6 reverse-Cross and Cross Entropy Concepts = 57
 4.7 Activation Rule = 59
 4.8 Entropy at Equilibrium = 59
 4.9 Boltzmann Machine as a Connectionist Model = 61
 4.10 Pseudo-Thermodynamic Perspectives of Learning Process = 63
 4.11 Learning from Examples Generated by a Perceptron = 65
 4.12 Learning at Zero Temperature = 67
 4.13 Concluding Remarks = 69
Chapter 5 : The Physics of Neural Activity : A Statistical Mechanics Perspective
 5.1 Introduction = 72
 5.2 Cragg and Temperley Model = 74
 5.3 Concerns of Griffith = 76
 5.4 Little's Model = 78
 5.5 Thompson and Gibson Model = 85
 5.6 Hopfield's Model = 87
 5.7 Peretto's Model = 89
 5.8 Little's Model versus Hopfield's Model = 91
 5.9 Ising Spin System versus Interacting Neurons = 94
 5.10 Liquid-Crystal Model = 94
 5.11 Free-Point Molecular Dipole Interactions = 98
 5.12 Stochastical Response of Neurons under Activation = 102
 5.13 Hamiltonian of Neural Spatial Long-Range Order = 105
 5.14 Spatial persistence in the Nematic Phase = 105
 5.15 Langevin Machine = 106
 5.16 Langevin Machine versus Boltzmann Machine = 108
 5.17 Concluding Remarks = 109
Chapter 6 : Stochastical Dynamics of the Neural Complex
 6.1 Introduction = 110
 6.2 Stochastical Dynamics of the Neural Assembly = 110
 6.3 Correlation of Neuronal-State Disturbances = 112
 6.4 Fokker-Planck Equation of Neural Dynamics = 116
 6.5 Stochastical Instability in Neural Networks = 118
 6.6 Stochastical Bounds and Estimates of Neuronal Activity = 121
 6.7 Stable States Search via Modified Bias Parameter = 125
 6.8 Noise-Induced Effects on Saturated Neural Population = 126
 6.9 Concluding Remarks = 128
Chapter 7 : Neural Field Theory : Quasiparticle Dynamics and Wave Mechanics Analogies of Neural Networks
 7.1 Introduction = 130
 7.2 "Momentum-Flow" Model of Neural Dynamics = 131
 7.3 Neural "Particle" Dynamics = 136
 7.4 Wave Mechanics Representation of Neural Activity = 141
 7.5 Characteristics of Neuronal Wave Function = 144
 7.6 Concepts of Wave Mechanics versus Neural Dynamics = 147
 7.7 Lattice Gas System Analogy of Neural Assembly = 149
 7.8 The Average Rate of Neuronal Transmission Flow = 151
 7.9 Models of Peretto and Little Versus "Neuronal Wave" = 152
 7.10 Wave Functional Representation of Hopfield's Network = 154
 7.11 Concluding Remarks = 156
Chapter 8 : Informatic Aspects of Neurocybernetics
 8.1 Introduction = 160
 8.2 Information-Theoretics of Neural Networks = 161
 8.3 Information Base of Neurocybernetics = 166
 8.4 Informatics of Neurocybernetic Processes = 170
 8.5 Disorganization in the Neural System = 171
 8.6 Entropy of Neurocybernetic Self-Regulation = 175
 8.7 Subjective Neural Disorganization  = 177
 8.8 Continuous Neural Entropy = 179
 8.9 Dfferential Disorganization in the Neural Complex = 180
 8.10 Dynamic Characteristics of Neural Informatics = 181
 8.11 Jensen-Shannon Divergence Measure = 182
 8.12 Semiotic Framework of Neuroinformatics = 186
 8.13 Informational Flow in the Neural control Process = 190
 8.14 Dynamic State of Neural Organization = 193
 8.15 Concluding Remarks = 194
Appendix A : Magnetism and the Ising Spin-Glass Model = 196
 A.1 General = 196
 A.2 Paramagnetism = 197
 A.3 Ferromagnetism = 198
 A.4 Antiferromagnetism = 198
 A.5 Ferrimagnetism = 198
 A.6 Magnetization = 198
 A.7 Spin-Glass Model = 199
 A.8 The Hamiltonian = 201
 A.9 Bonds and Sites = 201
 A.10 The Hard Spin = 202
 A.11 Quenching and Annealing = 202
 A.12 Frustration = 203
 A.13 Partition Function  = 204
 A.14 Ising Model : A Summary = 204
 A.15 Total Energy = 206
 A.16 Sigmoidal Function = 207
 A.17 Free Energy = 208
 A.18 Entropy = 208
Appendix B : Matrix Methods in Little's Model = 210
 B.1 A Short Review on Matrix Theory = 210
 B.2 Persistent States and Occurrence of Degeneracy in the Maximum Eigenvalue of the Transition Matrix = 215
 B.3 Diagonalizability of the Characteristic Matrix = 217
Appendix C : Overlap of Replicas and Replica symmetry Ansatz = 220
Bibliography = 222
Subject Index = 233