LT World

You are here: Home kb Information & Knowledge Technologies Connectionist Techniques

Connectionist Techniques

An Introduction to Natural Computation.
Dana H. Ballard.
Bradford, MIT Press. Cambridge, London. 1999.

From Word Stream to Gestalt: A Direct Semantic Parse for Complex Sentences. Technical Report AI 98-274.

  • Neural Theory of Language Research Group
  • Neural Networks Research Group
  • Department of Cognitive Science
  • Center for the Neural Basis of Cognition
  • Machine Learning and Neural Networks Group

  • Lokendra Shastri
  • Jeff Elman
  • Stan C. Kwasny
  • James L. McClelland
  • Risto Miikkulainen
  • James Hammerton

  • Subsymbolic Parsing of Sequences (SARDSRN)
  • Forming Text Representations with Neural Networks

Connectionist techniques are modelled on biological brains, whose higher-order cognitive processes appear to emerge from the interplay of large numbers of simple processing units, the neurons. Rather than being used as a substrate in which to implement known elements playing known roles, neural networks are let to evolve by themselves: they gradually adapt to the environment through a modification of inter-neural connection strengths, which come to reflect the neurons' history of co-activities. Typically, the emerging network represents objects, symbols, attributes, etc. (if at all) in states, involving larger numbers of neurons. Connectionism is a field of machine learning and has an affinity to statistics, fuzzy logic, and genetic programming.


Parallel Distributed Processing; Connectionism