An MCMC-Based Method of Comparing Connectionist Models in Cognitive Science

Despite the popularity of connectionist models in cognitive science, their performance can often be difficult to evaluate. Inspired by the geometric approach to statistical model selection, we introduce a conceptually similar method to examine the global behavior of a connectionist model, by counting the number and types of response patterns it can simulate. The Markov Chain Monte Carlo-based algorithm that we constructed finds these patterns efficiently. We demonstrate the approach using two localist network models of speech perception.