Pearlmutter, Barak A. and Hinton, Geoffrey (1986) G-Maximization: an Unsupervised Learning Procedure for Discovering Regularities. AIP Conference Proceedings, 151. pp. 333-338. ISSN 0094-243X

Preview

Download (416kB) | Preview

Abstract

Hill climbing is used to maximize an information theoretic measure of the difference between the actual behavior of a unit and the behavior that would be predicted by a statistician who knew the first order statistics of the inputs but believed them to be independent. This causes the unit to detect higher order correlations among its inputs. Initial simulations are presented, and seem encouraging. We describe an extension of the basic idea which makes it resemble competitive learning and which causes members of a population of these units to differentiate, each extracting different structure from the input.

Item Type:	Article
Keywords:	G-Maximization; Unsupervised Learning Procedure; Discovering Regularities;
Academic Unit:	Faculty of Science and Engineering > Computer Science Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	5533
Depositing User:	Barak Pearlmutter
Date Deposited:	03 Nov 2014 16:07
Journal or Publication Title:	AIP Conference Proceedings
Publisher:	American Institute of Physics
Refereed:	Yes
URI:	Publisher
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads