A state of the art specialist monograph on artificial neural networks which use Hebbian learning, covering a wide range of real experiments and which displays how it's approaches can be applied to analyse real problems. The book has a thorough approach and brings together a wide range of concepts into a coherent whole. Colin Fyfe writes with authority, and is a well-known, experienced researcher who has led a team working in this area at Paisley.

Concentrates on one specific architecture and learning rule which no other book does State of the art in artificial neural networks which use Hebbian learning A comparative study of a variety of techniques that have been drawn from extensions of one network The close link between statistics and artificial neural networks is made clear No other direct competition

Inhalt
Single Stream Networks.- Background.- The Negative Feedback Network.- Peer-Inhibitory Neurons.- Multiple Cause Data.- Exploratory Data Analysis.- Topology Preserving Maps.- Maximum Likelihood Hebbian Learning.- Dual Stream Networks.- Two Neural Networks for Canonical Correlation Analysis.- Alternative Derivations of CCA Networks.- Kernel and Nonlinear Correlations.- Exploratory Correlation Analysis.- Multicollinearity and Partial Least Squares.- Twinned Principal Curves.- The Future.