ISBN-10:
0262011972
ISBN-13:
9780262011976
Pub. Date:
11/22/2002
Publisher:
MIT Press
The Handbook of Brain Theory and Neural Networks / Edition 2

The Handbook of Brain Theory and Neural Networks / Edition 2

by Michael A. Arbib

Hardcover

Current price is , Original price is $19.75. You

Temporarily Out of Stock Online

Please check back later for updated availability.

This item is available online through Marketplace sellers.

Overview

A new, dramatically updated edition of the classic resource on the constantly evolving fields of brain theory and neural networks.

Dramatically updating and extending the first edition, published in 1995, the second edition of The Handbook of Brain Theory and Neural Networks presents the enormous progress made in recent years in the many subfields related to the two great questions: How does the brain work? and, How can we build intelligent machines?

Once again, the heart of the book is a set of almost 300 articles covering the whole spectrum of topics in brain theory and neural networks. The first two parts of the book, prepared by Michael Arbib, are designed to help readers orient themselves in this wealth of material. Part I provides general background on brain modeling and on both biological and artificial neural networks. Part II consists of "Road Maps" to help readers steer through articles in part III on specific topics of interest. The articles in part III are written so as to be accessible to readers of diverse backgrounds. They are cross-referenced and provide lists of pointers to Road Maps, background material, and related reading.

The second edition greatly increases the coverage of models of fundamental neurobiology, cognitive neuroscience, and neural network approaches to language. It contains 287 articles, compared to the 266 in the first edition. Articles on topics from the first edition have been updated by the original authors or written anew by new authors, and there are 106 articles on new topics.

Product Details

ISBN-13: 9780262011976
Publisher: MIT Press
Publication date: 11/22/2002
Series: A Bradford Book
Edition description: second edition
Pages: 1308
Product dimensions: 8.50(w) x 11.00(h) x 2.50(d)
Age Range: 18 Years

About the Author

Michael Arbib has played a leading role at the interface of neuroscience and computer science ever since his first book, Brains, Machines, and Mathematics. From Neuron to Cognition provides a worthy pedagogical sequel to his widely acclaimed Handbook of Brain Theory and Neural Networks. After thirty years at University of Southern California he is now pursuing interests in “how the brain got language” and “neuroscience for architecture” in San Diego.

Table of Contents

Preface ix(4)
How to Use This Book xiii
Part I: Background 1(26)
How to Use Part I 3(1)
I.1 Introducing the Neuron
4(7)
Basic Properties of Neurons
4(3)
Receptors and Effectors
7(1)
Neural Models
8(2)
More Detailed Properties of Neurons
10(1)
References
11(1)
I.2. Levels and Styles of Analysis
11(6)
A Historical Fragment
11(2)
Brains, Machines, and Minds
13(1)
Levels of Analysis
14(2)
References
16(1)
I.3. Dynamics and Adaptation in Neural Networks
17(10)
Dynamic Systems
17(3)
Adaptation in Dynamic Systems
20(5)
References
25(2)
Part II: Road Maps 27(32)
The Meta-Map
29(2)
II.1. Connectionism: Psychology, Linguistics, and Artificial Intelligence
31(3)
Connectionist Psychology
31(1)
Connectionist Linguistics
32(1)
Artificial Intelligence and Neural Networks
33(1)
II.2. Dynamics, Self-Organization, and Cooperativity
34(3)
Dynamic Systems and Optimization
34(1)
Cooperative Phenomena
35(1)
Self-Organization in Neural Networks
36(1)
II.3. Learning in Artificial Neural Networks
37(4)
Learning in Artificial Neural Networks, Deterministic
37(1)
Learning in Artificial Neural Networks, Statistical
38(2)
Computability and Complexity
40(1)
II.4. Applications and Implementations
41(4)
Control Theory and Robotics
41(1)
Applications of Neural Networks
42(1)
Implementation of Neural Networks
43(2)
II.5. Biological Neurons and Networks
45(5)
Biological Neurons
45(1)
Biological Networks
46(2)
Mammalian Brain Regions
48(2)
II.6. Sensory Systems
50(3)
Vision
50(2)
Other Sensory Systems
52(1)
II.7. Plasticity in Development and Learning
53(2)
Mechanisms of Neural Plasticity
53(1)
Development and Regeneration of Neural Networks
54(1)
Learning in Biological Systems
54(1)
II.8. Motor Control
55(4)
Motor Pattern Generators and Neuroethology
55(1)
Biological Motor Control
56(1)
Primate Motor Control
57(2)
Part III: Articles 59(1002)
Active Vision
61(2)
Activity-Dependent Regulation of Neuronal Conductances
63(3)
Adaptive Control: General Methodology
66(3)
Adaptive Control: Neural Network Applications
69(5)
Adaptive Filtering
74(5)
Adaptive Resonance Theory (ART)
79(3)
Adaptive Signal Processing
82(4)
Analog VLSI for Neural Networks
86(5)
Analogy-Based Reasoning
91(3)
Applications of Neural Networks
94(4)
Artificial Intelligence and Neural Networks
98(4)
Associative Networks
102(5)
Astronomy
107(3)
Auditory Cortex
110(5)
Auditory Periphery and Cochlear Nucleus
115(4)
Automata and Neural Networks
119(4)
Automatic Target Recognition
123(3)
Averaging/Modular Techniques for Neural Networks
126(3)
Axonal Modeling
129(5)
Backpropagation: Basics and New Developments
134(5)
Basal Ganglia
139(5)
Bayesian Methods for Supervised Neural Networks
144(5)
Bayesian Networks
149(4)
BCM Theory of Visual Cortical Plasticity
153(4)
Binding in the Visual System
157(2)
Biomaterials for Intelligent Systems
159(3)
Boltzmann Machines
162(4)
Cellular Automata
166(3)
Cerebellum and Conditioning
169(3)
Cerebellum and Motor Control
172(6)
Chains of Coupled Oscillators
178(5)
Chaos in Axons
183(3)
Chaos in Neural Systems
186(3)
Classical Learning Theory and Neural Networks
189(4)
Cognitive Development
193(4)
Cognitive Maps
197(3)
Cognitive Modeling: Psychology and Connectionism
200(3)
Collective Behavior of Coupled Oscillators
203(3)
Collicular Visuomotor Transformations for Saccades
206(4)
Color Perception
210(5)
Command Neurons and Command Systems
215(5)
Competitive Learning
220(3)
Compositionality in Neural Systems
223(3)
Computer Modeling Methods for Neurons
226(4)
Computing with Attractors
230(4)
Concept Learning
234(4)
Conditioning
238(5)
Connectionist and Symbolic Representations
243(4)
Consciousness, Theories of
247(3)
Constrained Optimization and the Elastic Net
250(5)
Convolutional Networks for Images, Speech, and Time Series
255(3)
Cooperative Behavior in Networks of Chaotic Elements
258(3)
Cooperative Phenomena
261(5)
Corollary Discharge in Visuomotor Coordination
266(3)
Cortical Columns, Modules, and Hebbian Cell Assemblies
269(3)
Coulomb Potential Learning
272(3)
Crustacean Stomatogastric System
275(3)
Data Clustering and Learning
278(4)
Dendritic Processing
282(7)
Dendritic Spines
289(3)
Developmental Disorders
292(3)
Development and Regeneration of Eye-Brain Maps
295(4)
Diffusion Models of Neuron Activity
299(5)
Digital VLSI for Neural Networks
304(5)
Directional Selectivity in the Cortex
309(3)
Directional Selectivity in the Retina
312(3)
Disease: Neural Network Models
315(3)
Dissociations Between Visual Processing Modes
318(3)
Distortions in Human Memory
321(1)
Distributed Artificial Intelligence
322(4)
Dynamic Clamp: Computer-Neural Hybrids
326(3)
Dynamic Link Architecture
329(3)
Dynamic Models of Neurophysiological Systems
332(3)
Dynamic Remapping
335(4)
Dynamics and Bifurcation of Neural Networks
339(5)
Echolocation: Creating Computational Maps
344(4)
EEG Analysis
348(4)
Electrolocation
352(4)
Emotion and Computational Neuroscience
356(4)
Emotion-Cognition Interactions
360(3)
Energy Functions for Neural Networks
363(4)
Epilepsy: Network Models of Generation
367(3)
Equilibrium Point Hypothesis
370(3)
Evolution of the Ancestral Vertebrate Brain
373(4)
Expert Systems and Decision Systems Using Neural Networks
377(4)
Exploration in Active Learning
381(4)
Eye-Hand Coordination in Reaching Movements
385(3)
Face Recognition
388(2)
Fault Tolerance
390(5)
Figure-Ground Separation
395(4)
Forecasting
399(4)
Fractal Strategies for Neural Network Scaling
403(3)
Frog Wiping Reflexes
406(4)
Fuzzy Logic Systems and Qualitative Knowledge
410(4)
Gabor Wavelets for Statistical Pattern Recognition
414(6)
Gait Transitions
420(3)
Gaze Coding in the Posterior Parietal Cortex
423(3)
Generalization and Regularization in Nonlinear Learning Systems
426(5)
"Genotypes" for Neural Networks
431(3)
Geometrical Principles in Motor Control
434(4)
Grasping Movements: Visuomotor Transformations
438(3)
Habituation
441(3)
Half-Center Oscillators Underlying Rhythmic Movements
444(3)
Handwritten Digit String Recognition
447(3)
Head Movements: Multidimensional Modeling
450(4)
Hebbian Synaptic Plasticity
454(5)
Hebbian Synaptic Plasticity: Comparative and Developmental Aspects
459(5)
High-Energy Physics
464(4)
Hippocampus: Spatial Models
468(4)
Human Movement: A System-Level Approach
472(5)
Identification and Control
477(4)
Illusory Contour Formation
481(3)
Information Theory and Visual Plasticity
484(3)
Invertebrate Models of Learning: Aplysia and Hermissenda
487(4)
Investment Management: Tactical Asset Allocation
491(5)
Ion Channels: Keys to Neuronal Specialization
496(5)
Kolmogorov's Theorem
501(2)
Language Acquisition
503(3)
Language Change
506(2)
Language Processing
508(5)
Layered Computation in Neural Networks
513(3)
Learning and Generalization: Theoretical Bounds
516(6)
Learning and Statistical Inference
522(5)
Learning as Adaptive Control of Synaptic Matrices
527(4)
Learning as Hill-Climbing in Weight Space
531(2)
Learning by Symbolic and Neural Methods
533(4)
Learning Vector Quantization
537(3)
Lesioned Attractor Networks as Models of Neuropsychological Deficits
540(3)
Limb Geometry: Neural Control
543(3)
Linguistic Morphology
546(3)
Localized Versus Distributed Representations
549(4)
Locomotion, Invertebrate
553(3)
Locust Flight: Components and Mechanisms in the Motor
556(4)
Long-Term Depression in the Cerebellum
560(4)
Markov Random Field Models in Image Processing
564(4)
Memory-Based Reasoning
568(2)
Mental Arithmetic Using Neural Networks
570(2)
Minimum Description Length Analysis
572(4)
Model-Reference Adaptive Control
576(3)
Modular and Hierarchical Learning Systems
579(3)
Modular Neural Net Systems, Training of
582(3)
Motion Perception
585(4)
Motion Perception: Self-Organization
589(2)
Motivation
591(3)
Motoneuron Recruitment
594(3)
Motor Control, Biological and Theoretical
597(3)
Motor Pattern Generation
600(5)
Multiprocessor Simulation of Neural Networks
605(4)
Muscle Models
609(4)
Neocognitron: A Model for Visual Pattern Recognition
613(4)
Neural Optimization
617(5)
Neuroanatomy in a Computational Perspective
622(4)
Neuroethology, Computational
626(5)
Neuromodulation in Invertebrate Nervous Systems
631(3)
Neurosimulators
634(5)
Neurosmithing: Improving Neural Network Learning
639(5)
NMDA Receptors: Synaptic, Cellular, and Network Models
644(4)
Noise Canceling and Channel Equalization
648(3)
Nonmonotonic Neuron Associative Memory
651(3)
NSL: Neural Simulation Language
654(4)
Object Recognition
658(2)
Ocular Dominance and Orientation Columns
660(5)
Olfactory Bulb
665(4)
Olfactory Cortex
669(4)
Optical Architectures for Neural Network Implementations
673(4)
Optical Components for Neural Network Implementations
677(5)
Optimization Principles in Motor Control
682(4)
Oscillatory and Bursting Properties of Neurons
686(5)
Oscillatory Associative Memories
691(3)
PAC Learning and Neural Networks
694(4)
Pain Networks
698(4)
Parallel Computational Models
702(3)
Pattern Formation, Biological
705(6)
Pattern Recognition
711(4)
Perception of Three-Dimensional Structure
715(4)
Perceptrons, Adalines, and Backpropagation
719(6)
Perceptual Grouping
725(3)
Perspective on Neuron Model Complexity
728(4)
Phase-Plane Analysis of Neural Activity
732(6)
Philosophical Issues in Brain Theory and Connectionism
738(3)
Planning, Connectionist
741(4)
Post-Hebbian Learning Rules
745(4)
Potential Fields and Neural Networks
749(4)
Principal Component Analysis
753(3)
Problem Solving, Connectionist
756(4)
Process Control
760(4)
Programmable Neurocomputing Systems
764(4)
Prosthetics, Neural
768(4)
Protein Structure Prediction
772(3)
Pursuit Eye Movements
775(4)
Radial Basis Function Networks
779(4)
Reaching: Coding in Motor Cortex
783(5)
Reaching Movements: Implications of Connectionist Models
788(5)
Reactive Robotic Systems
793(3)
Recurrent Networks: Supervised Learning
796(4)
Regularization Theory and Low-Level Vision
800(4)
Reinforcement Learning
804(5)
Reinforcement Learning in Motor Control
809(4)
Respiratory Rhythm Generation
813(3)
Retina
816(4)
Robot Control
820(3)
Routing Networks in Visual Cortex
823(3)
Saccades and Listing's Law
826(4)
Schema Theory
830(4)
Scratch Reflex
834(3)
Selective Visual Attention
837(3)
Self-Organization and the Brain
840(3)
Self-Organization in the Time Domain
843(3)
Self-Organizing Feature Maps: Kohonen Maps
846(5)
Self-Reproducing Automata
851(3)
Semantic Networks
854(3)
Sensor Fusion
857(3)
Sensorimotor Learning
860(4)
Sensory Coding and Information Theory
864(3)
Short-Term Memory
867(4)
Silicon Neurons
871(5)
Simulated Annealing
876(3)
Single-Cell Models
879(5)
Somatosensory System
884(4)
Somatotopy: Plasticity of Sensory Maps
888(3)
Sound Localization and Binaural Processing
891(4)
Sparse Coding in the Primate Cortex
895(4)
Sparsely Coded Neural Networks
899(3)
Spatiotemporal Association in Neural Networks
902(3)
Speaker Identification
905(2)
Speech Recognition: A Hybrid Approach
907(3)
Speech Recognition: Feature Extraction
910(3)
Speech Recognition: Pattern Matching
913(5)
Spinal Cord of Lamprey: Generation of Locomotor Patterns
918(4)
Statistical Mechanics of Generalization
922(3)
Statistical Mechanics of Learning
925(5)
Statistical Mechanics of Neural Networks
930(4)
Steelmaking
934(3)
Stereo Correspondence and Neural Networks
937(4)
Stochastic Approximation and Neural Network Learning
941(4)
Structural Complexity and Discrete Neural Networks
945(4)
Structured Connectionist Models
949(4)
Synaptic Coding of Spike Trains
953(3)
Synaptic Currents, Neuromodulation, and Kinetic Models
956(4)
Synchronization of Neuronal Responses as a Putative Binding Mechanism
960(4)
Telecommunications
964(3)
Temporal Pattern Processing
967(4)
Textured Images: Modeling and Segmentation
971(5)
Thalamocortical Oscillations in Sleep and Wakefulness
976(5)
Thalamus
981(3)
Time Complexity of Learning
984(3)
Time Perception: Problems of Representation and Processing
987(3)
Topology-Modifying Neural Network Algorithms
990(4)
Traveling Activity Waves
994(3)
Unsupervised Learning with Global Objective Functions
997(3)
Vapnik-Chervonenkis Dimension of Neural Networks
1000(3)
Vestibulo-Ocular Reflex: Performance and Plasticity
1003(5)
Vision for Robot Driving
1008(1)
Vision: Hyperacuity
1009(3)
Visual Coding, Redundancy, and "Feature Detection"
1012(4)
Visual Cortex Cell Types and Connections
1016(5)
Visual Processing of Object Form and Environment Layout
1021(3)
Visual Scene Perception: Neurophysiology
1024(5)
Visual Schemas in Object Recognition and Scene Analysis
1029(2)
Visuomotor Coordination in Flies
1031(5)
Visuomotor Coordination in Frogs and Toads
1036(6)
Visuomotor Coordination in Salamanders
1042(3)
Walking
1045(4)
Wavelet Dynamics
1049(5)
Wave Propagation in Cardiac Muscle and in Nerve Networks
1054(2)
Winner-Take-All Mechanisms
1056(5)
Editorial Advisory Board 1061(2)
Contributors 1063(12)
Subject Index 1075

What People are Saying About This

Joaquin M. Fuster

The awesome product of an awesome task, this book will take us into the 21st Century with a wide and enlightened overview of computational neuroscience—and a healthy respect for the constraints that the real brain imposes on our models. Arbib has done what urgently needed to be done and what probably no one else could do.

Professor Jerry A. Feldman

No existing work comes close to covering the same range of topics in such an authoritative way. The editor has gone far beyond the usual collection of articles in providing roadmaps and cross-references for each topic. Judging from the articles that I have read and from the list of authors, the Handbook will become an invaluable resource to a wide range of researchers.

Endorsement

This revised Handbook of Brain Theory provides useful new data and and updates key concepts in neuroscience. It will be an indispensable guide for exploring the essentials of brain science.

Masao Ito, RIKEN Brain Science Institute

William H. Calvin

It's been a half century since such pioneers as Warren McCulloch and Donald Hebb, and, particularly in the last decade, brain theory has been in flower, intertwining with both neurophysiology and artificial neural networks. Boiling it down and concentrating it, as this handbook does so successfully,is likely to set the stage for something even more interesting.

From the Publisher

Today, neuroscience gives us great dual hopes, one to radically solve medical problems of the brain such as Arzheimer's disease, and the other to give an answer to the long-standing question of how the brain works to yield our mind. Medical achievements will be obtained based on accumulated knowledge of molecular and cellular events of the brain, but the understanding of the brain mechansims of mental activities requires theories and models. This handbook summerizes the success of neuroscience in developing such theories and models, and further provides a basis for future achievements toward the goal. It will help not only theorists, but also experimentalists to grasp the great potentially of theories and models in future neuroscience.

Masao Ito , Director-General, Frontier Research Program, The Institute of Physical and Chemical Research

No existing work comes close to covering the same range of topics in such an authoritative way. The editor has gone far beyond the usual collection of articles in providing roadmaps and cross-references for each topic. Judging from the articles that I have read and from the list of authors, the Handbook will become an invaluable resource to a wide range of researchers.

Professor Jerry A. Feldman , International Computer Science Institute and University of California

It's been a half century since such pioneers as Warren McCulloch and Donald Hebb, and, particularly in the last decade, brain theory has been in flower, intertwining with both neurophysiology and artificial neural networks. Boiling it down and concentrating it, as this handbook does so successfully,is likely to set the stage for something even more interesting.

William H. Calvin , University of Washington neurophysiologist, author of The Ascent of Mind and co-author of Conversations with Neil's Brain

At long last neural computation, as a wide interdisciplinary field, has found its universal, intellectual home. Under one roof we have all that we wanted to know from the biological to the matehmatical, from experiment to theory, from applications to abstract models, from robots to philosophy.

Daniel Amit , Professor at the University of Rome and the university of Jerusalem; author of Modeling Brain Fuction

The awesome product of an awesome task, this book will take us into the 21st Century with a wide and enlightened overview of computational neuroscience—and a healthy respect for the constraints that the real brain imposes on our models. Arbib has done what urgently needed to be done and what probably no one else could do.

Joaquin M. Fuster , Professor of Psychiatry and Biobehavioral Sciences, School of Medicine, University of California

This revised Handbook of Brain Theory provides useful new data and and updates key concepts in neuroscience. It will be an indispensable guide for exploring the essentials of brain science.

Masao Ito , RIKEN Brain Science Institute

Masao Ito

This revised Handbook of Brain Theory provides useful new data and and updates key concepts in neuroscience. It will be an indispensable guide for exploring the essentials of brain science.

Daniel Amit

At long last neural computation, as a wide interdisciplinary field, has found its universal, intellectual home. Under one roof we have all that we wanted to know from the biological to the matehmatical, from experiment to theory, from applications to abstract models, from robots to philosophy.

Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews