E-insensitive Unsupervised Learning.

Fyfe, C. and Gabrys, B., 1999. E-insensitive Unsupervised Learning. In: International Conference on Neural Networks and Artificial Intelligence (ICNNAI'99), October 1999, Brest, Belarus, pp. 10-18.

Full text available as:

[img]
Preview
PDF
140kB

Abstract

One of the major paradigms for unsupervised learning in Artificial Neural Networks is Hebbian learning. The standard implementations of Hebbian learning are optimal under the assumptions of Gaussian noise in a data set. We derive e-insensitive Hebbian learning based on minimising the least absolute error in a compressed data set and show that the learning rule is equivalent to the Principal Component Analysis (PCA) networks' learning rules under a variety of conditions.

Item Type:Conference or Workshop Item (Paper)
Subjects:Generalities > Computer Science and Informatics > Artificial Intelligence
Generalities > Computer Science and Informatics
Group:School of Design, Engineering & Computing
ID Code:9641
Deposited By:Professor Bogdan Gabrys
Deposited On:11 Mar 2009 21:36
Last Modified:07 Mar 2013 15:07

Document Downloads

More statistics for this item...
Repository Staff Only -
BU Staff Only -
Help Guide - Editing Your Items in BURO