author : Richard G. Palmer

Contents:

1. Introduction
2. The Hopfield model
   • associative memory • statistical mechanics • stochastic networks
3. Extensions of the Hopfield model
4. Optimization problems
5. Simple perceptrons
   • feed-forward networks • proof of convergence • linear, non-linear, stochastic units
6. Multi-layer networks
   • back-propagation
7. Recurrent networks
   • Boltzmann machines
8. Unsupervised Hebbian learning
   • principal component analysis • self-organizing feature extraction
9. Unsupervised competitive learning
   • adaptive resonance theory
10. Formal statistical mecanics of neural networks