Fodor and Pylyshyn's Critique of Connectionism and the Brain as Basis of the Mind

TL;DR

This paper reviews the historical debate between connectionist and classical approaches to understanding the mind-brain relationship, critiques their limitations, and proposes a synthesis through structured neural networks.

Contribution

It offers a new perspective by proposing structured, self-organized neural networks as a synthesis of connectionist and classical theories.

Findings

Critique of connectionism and classical approaches

Proposal of structured, self-organized neural networks

Potential for new insights into mind-brain correspondence

Abstract

To this day there is no satisfactory answer to the question how mental patterns correspond to physical states of our brain. For more than six decades, progress has been held up by the logjam between two traditions, one inspired by neuroscience, the other by digital computing. This logjam is well illuminated by Fodor and Pylyshyn's article of 1988, which is mainly devoted to a critique of what they call Connectionism, but also lays bare weaknesses of the Classical approach which they defend. As recent machine learning breakthroughs may be expected to through new light on the issue, it seems time to arrive at a synthesis of the connectionist neural approach and the classical stance based on symbol processing. I will present and discuss an attempt at such synthesis in the form of structured, self-organized neural networks.