University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Evolutionary multi-objective optimization for simultaneous generation of signal-type and symbol-type representations

Jin, Y, Sendhoff, B and Körner, E (2005) Evolutionary multi-objective optimization for simultaneous generation of signal-type and symbol-type representations

[img] Text
EMO05_F.pdf
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (214kB)
[img] Text (licence)
SRI_deposit_agreement.pdf
Restricted to Repository staff only

Download (33kB)

Abstract

It has been a controversial issue in the research of cognitive science and artificial intelligence whether signal-type representations (typically connectionist networks) or symbol-type representations (e.g., semantic networks, production systems) should be used. Meanwhile, it has also been recognized that both types of information representations might exist in the human brain. In addition, symbol-type representations are often very helpful in gaining insights into unknown systems. For these reasons, comprehensible symbolic rules need to be extracted from trained neural networks. In this paper, an evolutionary multi-objective algorithm is employed to generate multiple models that facilitate the generation of signal-type and symbol-type representations simultaneously. It is argued that one main difference between signal-type and symbol-type representations lies in the fact that the signal-type representations are models of a higher complexity (fine representation), whereas symbol-type representations are models of a lower complexity (coarse representation). Thus, by generating models with a spectrum of model complexity, we are able to obtain a population of models of both signal-type and symbol-type quality, although certain post-processing is needed to get a fully symbol-type representation. An illustrative example is given on generating neural networks for the breast cancer diagnosis benchmark problem. © Springer-Verlag Berlin Heidelberg 2005.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Authors :
NameEmailORCID
Jin, YUNSPECIFIEDUNSPECIFIED
Sendhoff, BUNSPECIFIEDUNSPECIFIED
Körner, EUNSPECIFIEDUNSPECIFIED
Date : 2005
Identification Number : 10.1007/978-3-540-31880-4_52
Contributors :
ContributionNameEmailORCID
http://www.loc.gov/loc.terms/relators/PBLSpringer, UNSPECIFIEDUNSPECIFIED
Depositing User : Symplectic Elements
Date Deposited : 28 Mar 2017 14:42
Last Modified : 31 Oct 2017 14:35
URI: http://epubs.surrey.ac.uk/id/eprint/532843

Actions (login required)

View Item View Item

Downloads

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