Hebbian Learning and Negative Feedback Networks by Colin FyfeHebbian Learning and Negative Feedback Networks by Colin Fyfe

Hebbian Learning and Negative Feedback Networks

byColin Fyfe

Hardcover | January 5, 2005

Pricing and Purchase Info

$227.75 online 
$245.95 list price save 7%
Earn 1,139 plum® points

Prices and offers may vary in store


In stock online

Ships free on orders over $25

Not available in stores


The central idea of Hebbian Learning and Negative Feedback Networks is that artificial neural networks using negative feedback of activation can use simple Hebbian learning to self-organise so that they uncover interesting structures in data sets. Two variants are considered: the first uses a single stream of data to self-organise. By changing the learning rules for the network, it is shown how to perform Principal Component Analysis, Exploratory Projection Pursuit, Independent Component Analysis, Factor Analysis and a variety of topology preserving mappings for such data sets. The second variants use two input data streams on which they self-organise. In their basic form, these networks are shown to perform Canonical Correlation Analysis, the statistical technique which finds those filters onto which projections of the two data streams have greatest correlation. The book encompasses a wide range of real experiments and displays how the approaches it formulates can be applied to the analysis of real problems.
Title:Hebbian Learning and Negative Feedback NetworksFormat:HardcoverDimensions:401 pagesPublished:January 5, 2005Publisher:Springer LondonLanguage:English

The following ISBNs are associated with this title:

ISBN - 10:1852338830

ISBN - 13:9781852338831

Look for similar items by category:


Table of Contents

Introduction Part I - Single Stream Networks Background The Negative Feedback Network Peer-Inhibitory Neurons Multiple Cause Data Exploratory Data Analysis Topology Preserving Maps Maximum Likelihood Hebbian Learning Part II - 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 App. A. Negative Feedback Artificial Neural Networks B. Previous Factor Analysis Models C. Related Models for ICA D. Previous Dual Stream Approaches E. Data Sets References Index

Editorial Reviews

From the reviews of the first edition:"This book is concerned with developing unsupervised learning procedures and building self organizing network modules that can capture regularities of the environment. . the book provides a detailed introduction to Hebbian learning and negative feedback neural networks and is suitable for self-study or instruction in an introductory course." (Nicolae S. Mera, Zentralblatt MATH, Vol. 1069, 2005)