Peretto P. An introduction to the modeling of neural networks

Cambridge University Press 1992, 492 c.Mind as an emergent property of nervous systems
Neuronal nets as automata networks: a brief historical overview
Organization of the book
The biology of neural networks: a few features for the sake of non-biologists
Three approaches to the study of the functioning of central nervous systems
The anatomy of central nervous systems
A brief survey of neurophysiology
Learning and memory: a summary of experimental observations
The dynamics of neural networks: a stochastic approach
Introducing the problem
Noiseless neural networks
Taking synaptic noise into account
Hebbian models of associative memory
Noiseless Hebbian models
Stochastic Hebbian neural networks in the limit of finite numbers of memorized patterns
Storing an infinite number of patterns in stochastic Hebbian networks: the technique of field distributions
The replica method approach
General dynamics of neural networks
Temporal sequences of patterns
Parallel dynamics
Stochastic dynamics
An example of conditioned behavior
The problem of learning in neural networks
Introducing the problem
Linear separability
Computing the volume of solutions
Learning dynamics in 'visible' neural networks
A classification of learning dynamics
Constraining the synaptic efficacies
Projection algorithms
The perceptron learning rules
Correlated patterns
Solving the problem of credit assignment
The back-propagation algorithm
Handling internal representations
Learning in Boolean networks
Self-organization
Self-organization in simple networks
Ontogenesis
Three questions about learning
Neurocomputation
Domains of applications of neural networks
Optimization
Low-level signal processing
Pattern matching
Some speculations on biological systems
Higher associative functions
Neurocomputers
General principles of neurocomputation
Semi-parallel neurocomputers
A critical view of the modeling of neural networks
Information structures the biological system
The neural code
The synfire chains
Computing with attractors versus computing with flows of information
The issue of low neuronal activities
Learning and cortical plasticity
Taking the modular organization of the cortex into account
Higher-order processing: the problem of artificial intelligence
Concluding remarks