Robert M. French (1998) Function, Sufficiently Constrained, Implies Form . Psycoloquy: 9(21) Connectionist Explanation (18)
Versions: ASCII formatted
Psycoloquy 9(21): Function, Sufficiently Constrained, Implies Form

FUNCTION, SUFFICIENTLY CONSTRAINED, IMPLIES FORM
Commentary on Green on Connectionist-Explanation

Robert M. French
Psychology Department (B33)
University of Liege,
4000 Liege, Belgium
http://www.fapse.ulg.ac.be/Lab/Trav/rfrench.html

Axel Cleeremans
Seminaire de Recherche en Sciences Cognitives
Universite Libre de Bruxelles
1050 Brussels, Belgium

rfrench@ulg.ac.be axcleer@ulb.ac.be

Abstract

Green's (1998) target article is an attack on most current connectionist models of cognition. Our commentary will suggest that there is an essential component missing in his discussion of modeling, namely, the idea that the appropriate level of the model needs to be specified. We will further suggest that the precise form (size, topology, learning rules, etc.) of connectionist networks will fall out as ever more detailed constraints are placed on their function.

Keywords

artificial intelligence, cognition, computer modelling, connectionism, epistemology, explanation, methodology, neural nets, philosophy of science, theory.

References