UNSPECIFIED (1994) INTEGER-WEIGHT NEURAL NETS. ELECTRONICS LETTERS, 30 (15). pp. 1237-1238. ISSN 0013-5194

Full text not available from this repository.

Abstract

Integer-weight neural nets (IWNN) are better suited for hardware implementation than their real-weight analogues. The authors present a learning procedure for generating multilayer IWNNs having all weights in the set {-3, -2, -1, 0, 1, 2, 3}. The performance of this procedure was evaluated on XOR, encoder/decoder and the MONK benchmark. The IWNNs were found to be as capable as their real-weight counterparts with regard to generalisation performance.

Item Type:	Journal Article
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Journal or Publication Title:	ELECTRONICS LETTERS
Publisher:	IEE-INST ELEC ENG
ISSN:	0013-5194
Date:	21 July 1994
Volume:	30
Number:	15
Number of Pages:	2
Page Range:	pp. 1237-1238
Publication Status:	Published
URI:	http://wrap.warwick.ac.uk/id/eprint/20420

Data sourced from Thomson Reuters' Web of Knowledge

Request changes to a record

Actions (login required)

View Item