University of Surrey

Test tubes in the lab Research in the ATI Dance Research

In-situ learning in multi-net systems

Casey, M, Ahmad, K, Yang, ZR, Everson, R and Yin, H (2004) In-situ learning in multi-net systems In: 5th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2004), 2004-08-25 - 2004-08-27, Execter, ENGLAND.

Available under License : See the attached licence file.

Download (36Kb)
[img] Plain Text (licence)

Download (1516b)


Multiple classifier systems based on neural networks can give proved generalisation performance as compared with single classifier systems. We examine collaboration in multi-net systems through in-situ learning exploring how generalisation can be improved through the simultaneous learning in networks and their combination. We present two in-situ trained systems; first, one based upon the simple ensemble, combining supervised networks in parallel, and second, a combination of unsupervised and supervised networks in, sequence. Results for these are compared with existing approaches demonstrating that in-situ trained systems perform better than similar pre-trained systems.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, Theory & Methods, Computer Science, CLASSIFIERS
Related URLs:
Divisions: Faculty of Engineering and Physical Sciences > Computing Science
Depositing User: Symplectic Elements
Date Deposited: 17 Jun 2011 16:03
Last Modified: 23 Sep 2013 18:42

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800