Layered Hybrid Connectionist Models for Cognitive Science

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Direct connnectionist modeling of higher cognitive functions, such as language understanding, is impractical. This chapter describes a principled multi-layer architecture that supports AI style computational modeling while preserving the biological plausibility of structured connectionist models. As an example, the connectionist realization of Bayesian model merging as recruitment learning is presented.