Swann, A. and Allinson, N. (1998) Fast committee learning: preliminary results. Electronics Letters, 34 (14). pp. 1408-1410. ISSN 1013-5194

PDF 00706104.pdf - Whole Document Restricted to Repository staff only Download (445Kb) | Request a copy

Abstract

Fast committee leaming can, to some extent, achieve the generalisation advantages of a committee of neural networks, without the need for independent leaming of the committee members. This is achieved by selecting committee members from time-slices of the learning trajectory of one neural nctwork.

Item Type:	Article
Additional Information:	Fast committee leaming can, to some extent, achieve the generalisation advantages of a committee of neural networks, without the need for independent leaming of the committee members. This is achieved by selecting committee members from time-slices of the learning trajectory of one neural nctwork.
Keywords:	algorithm, neural networks, fast committee learning, learning trajectory
Subjects:	G Mathematical and Computer Sciences > G730 Neural Computing
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Tammie Farley
Date Deposited:	23 Apr 2012 11:08
Last Modified:	13 Mar 2013 09:06
URI:	http://eprints.lincoln.ac.uk/id/eprint/5090

Actions (login required)

View Item