Chapter

Hybrid Neural Systems

Volume 1778 of the series Lecture Notes in Computer Science pp 14-27

Layered Hybrid Connectionist Models for Cognitive Science

  • Jerome FeldmanAffiliated withInternational Computer Science Institute
  • , David BaileyAffiliated withInternational Computer Science Institute

* 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.