Behavioral and Brain Sciences



Continuing Commentary
Commentary on Mike Page (2000). Connectionist modelling in psychology: A localist manifesto. BBS 23(4):443–512.

The local is running on the express track: Localist models better facilitate understanding of nervous system function


Paul A. Koch a1 and Gerry Leisman a2
a1 School of Engineering, New York Institute of Technology, Old Westbury, NY 11568 pkoch@liii.com
a2 Carrick Institute for Clinical Ergonomics, Rehabilitation and Applied Neurosciences, School of Engineering, State University of New York at Farmingdale, Farmingdale, NY 11735-1021 leismag@farmingdale.edu

Abstract

Artificial neural networks have weaknesses as models of cognition. A conventional neural network has limitations of computational power. The localist representation is at least equal to its competition. We contend that locally connected neural networks are perfectly capable of storing and retrieving the individual features, but the process of reconstruction must be otherwise explained. We support the localist position but propose a “hybrid” model that can begin to explain cognition in anatomically plausible terms.