Hebbian Learning and Negative Feedback Networks (Advanced Information and Knowledge Processing)

✍ Scribed by Colin Fyfe

• Year: 2004
• Tongue: English
• Leaves: 388
• Edition: 1st Edition.
• Category: Library

✦ Synopsis

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.

✦ Table of Contents

Cover......Page 1
Hebbian Learning and
Negative Feedback
Networks......Page 4
Advanced Information and Knowledge Processing......Page 2
ISBN 1852338830......Page 5
Contents......Page 7
Acronyms......Page 15
Preface......Page 16
1
Introduction......Page 18
Part I
Single Stream Networks......Page 23
2
Background......Page 26
3
The Negative Feedback Network......Page 45
4
Peer-Inhibitory Neurons......Page 71
5
Multiple Cause Data......Page 99
6
Exploratory Data Analysis......Page 124
7
Topology Preserving Maps......Page 150
8
Maximum Likelihood Hebbian Lear......Page 182
Part II
Dual Stream Networks......Page 200
9
Two Neural Networks for Canonical
Correlation Analysis......Page 203
10
Alternative Derivations of CCA Networks......Page 221
11
Kernel and Nonlinear Correlations......Page 229
12
Exploratory Correlation Analysis......Page 259
13
Multicollinearity and Partial Least Squares......Page 286
14
Twinned Principal Curves......Page 301
15
The Future......Page 318
A
Negative Feedback Artificial Neural Networks......Page 323
B
Previous Factor Analysis Models......Page 330
C
Related Models for ICA......Page 348
D
Previous Dual Stream Approaches......Page 360
E
Data Sets......Page 370
References......Page 377
Index......Page 386