Neural networks, nativism, and the plausibility of constructivism.

Recent interest in PDP (parallel distributed processing) models is due in part to the widely held belief that they challenge many of the assumptions of classical cognitive science. In the domain of language acquisition, for example, there has been much interest in the claim that PDP models might undermine nativism. Related arguments based on PDP learning have also been given against Fodor's anti-constructivist position--a position that has contributed to the widespread dismissal of constructivism. A limitation of many of the claims regarding PDP learning, however, is that the principles underlying this learning have not been rigorously characterized. In this paper, I examine PDP models from within the framework of Valiant's PAC (probably approximately correct) model of learning, now the dominant model in machine learning, and which applies naturally to neural network learning. From this perspective, I evaluate the implications of PDP models for nativism and Fodor's influential anti-constructivist position. In particular, I demonstrate that, contrary to a number of claims, PDP models are nativist in a robust sense. I also demonstrate that PDP models actually serve as a good illustration of Fodor's anti-constructivist position. While these results may at first suggest that neural network models in general are incapable of the sort of concept acquisition that is required to refute Fodor's anti-constructivist position, I suggest that there is an alternative form of neural network learning that demonstrates the plausibility of constructivism. This alternative form of learning is a natural interpretation of the constructivist position in terms of neural network learning, as it employs learning algorithms that incorporate the addition of structure in addition to weight modification schemes. By demonstrating that there is a natural and plausible interpretation of constructivism in terms of neural network learning, the position that nativism is the only plausible model of acquisition can no longer be defended. Indeed, I briefly discuss a number of learning-theoretic reasons indicating that constructivist models so characterized uniquely possess a number of important learning characteristics.