Self-organization of Multiple Winner-take-all Neural Networks
作者:
STEPHEN P LUTTRELL,
期刊:
Connection Science
(Taylor Available online 1997)
卷期:
Volume 9,
issue 1
页码: 11-30
ISSN:0954-0091
年代: 1997
DOI:10.1080/095400997116711
出版商: Taylor & Francis Group
关键词: Keywords: Self-organization;Firing Neurons;Winner-take-all;Factorial Network;Ocular Dominance
数据来源: Taylor
摘要:
In this paper, analysis of the information content of discretely firing neurons in unsupervised neural networks is presented, where information is measured according to the network's ability to reconstruct its input from its output with minimum mean square Euclidean error. It is shown how this type of network can self-organize into multiple winner-take-all subnetworks, each of which tackles only a low-dimensional subspace of the input vector. This is a rudimentary example of a neural network that effectively subdivides a task into manageable subtasks.
点击下载:
PDF (262KB)
返 回