Connectionist Techniques
abbreviation(s): PDP
definition: 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.
See also the corresponding HLT Survey chapter: http://www.lt-world.org/hlt_survey/ltw-chapter11-5.pdf
related project(s):
- SHRUTI
- Subsymbolic Parsing of Sequences (SARDSRN)
- Forming Text Representations with Neural Networks
related organisation(s):
- Neural Networks Research Group
- Neural Theory of Language Research Group
- Department of Cognitive Science
related person(s):
- James L. McClelland
- Lokendra Shastri
- James Hammerton
- Stan C. Kwasny
- Jeff Elman
- Risto Miikkulainen
relevant source(s):
related publication(s):
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.
Bobby