Computational Modeling of Variability in the Balance Scale Task

The study of variability in reasoning can shed light on several issues, including mechanisms underlying developmental change, individual differences, and developmental disorders. We explored the basis of variability in a much-studied task in cognitive development, the balance scale. Starting with a simple feed-forward connectionist model and training patterns based on McClelland (1989), we investigated computational parameters, problem encodings, and training environments that contribute to variability in development, both across groups and within individuals. We report on the parameters that affect the complexity of reasoning and the nature of ‘rule’ transitions exhibited by networks learning to reason about balance scale problems.