Changsin Lee, Bram van Heuveln, (1998) Why Connectionist Nets are Good Models . Psycoloquy: 9(17) Connectionist Explanation (14)
Versions: ASCII formatted
Psycoloquy 9(17): Why Connectionist Nets are Good Models

WHY CONNECTIONIST NETS ARE GOOD MODELS
Commentary on Green on Connectionist-Explanation

Changsin Lee, Bram van Heuveln,
Clayton T. Morrison & Eric Dietrich
PACCS, Department of Philosophy
Binghamton University
Binghamton, NY 13902
http://www.paccs.binghamton.edu/chang/

chang@turing.paccs.binghamton.edu

Abstract

We agree with Green that some connectionists do not make it clear what their nets are modeling. However, connectionism is still a viable project, connectionism, because it provides a different ontology and different ways of modeling cognition by requiring us to consider implementational details. We also argue against Green's view of models in science and his characterization of connectionist networks.

Keywords

cognition, connectionism, explanation, model, ontology, theory

References