Conference Proceeding

Information efficiency of the associative net at arbitrary coding rates

Details

Citation

Graham B & Willshaw DJ (1996) Information efficiency of the associative net at arbitrary coding rates. In: von der Malsburg C, von Seelen W, Vorbruggen J & Sendhoff B (eds.) Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings. Lecture Notes in Computer Science, 1112. ICANN 96: International Conference on Artificial Neural Networks, Bochum, Germany, 16.07.1996-19.07.1996. Berlin Heidelberg: Springer, pp. 35-40. http://link.springer.com/chapter/10.1007/3-540-61510-5_10; https://doi.org/10.1007/3-540-61510-5_10

Abstract
The associative net is a neural network model of associative memory that is unusual in having binary-valued connections between units. This net can work with high information efficiency, but only if the patterns to be stored are extremely sparse. In this paper we report how the efficiency of the net can be improved for more dense coding rates by using a partially-connected net. The information efficiency can be maintained at a high level over a 2-3 order of magnitude variation in the degree of pattern sparseness.

StatusPublished
Title of seriesLecture Notes in Computer Science
Number in series1112
Publication date31/12/1996
Publication date online31/07/1996
PublisherSpringer
Publisher URLhttp://link.springer.com/chapter/10.1007/3-540-61510-5_10
Place of publicationBerlin Heidelberg
ISSN of series0302-9743
ISBN978-3-540-61510-1
ConferenceICANN 96: International Conference on Artificial Neural Networks
Conference locationBochum, Germany
Dates

People (1)

People

Professor Bruce Graham

Professor Bruce Graham

Emeritus Professor, Computing Science