Beyond Associative Memory: Connectionists Must Search for Other Cognitive Primitives

Abstract

Many recent connectionist models can be categorized as associative memories or pattern classifiers. Viewed at the right level of abstraction, the two are the same. Connectionists sometimes appear to be trying to squeeze all of cognition into the associative memory paradigm, perhaps because it's the only thing they know how to implement with gradient descent learning algorithms. But the combinatorial structure of thought and language indicates that the answer to 'How can slow components think so fast' lies beyond mere associative recall. We must search for additional cognitive primitives that can be implemented in parallel hardware. One modest successor to associative recall is considered here. (eg)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 22, 1988
Accession Number
ADA218907

Entities

People

  • David S. Touretzky

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy
  • Counter IED

DTIC Thesaurus Topics

  • Classification
  • Computer Science
  • Computers
  • Content Addressable Memory
  • Contracts
  • Identification
  • Language
  • Learning
  • Military Research
  • Models
  • Pattern Recognition
  • Pennsylvania
  • Procurement
  • Recognition
  • Security
  • United States
  • Universities

Fields of Study

  • Psychology

Readers

  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.
  • Theoretical Analysis.