CONNECTIONISM AND THE LANGUAGE OF THOUGHT

In an influential critique, Jerry Fodor and Zenon Pylyshyn point to th e existence of a potentially devastating dilemma for connectionism (Fo dor and Pylyshyn [1988]). Either connectionist models consist in mere associations of unstructured representations, or they consist in proce sses involving complex representations. If the former, connectionism i s mere associationism, and will not be capable of accounting for very much of cognition. If the latter, then connectionist models concern on ly the implementation of cognitive processes, and are, therefore, not informative at the level of cognition. I shall argue that Fodor and Py lyshyn's argument is based on a crucial misunderstanding, the same mis understanding which motivates the entire language of thought hypothesi s.