Recruitment versus backpropagation learning: Re-learning in connectionist networks

Technical Report · Mon Jan 01 04:00:00 EST 1990

OSTI ID:5447719

Diederich, J

The paper describes a first comparison between two connectionist learning techniques: backpropagation and recruitment learning. The task is to re-learn a conceptual representation, i.e. to significantly change a representation in an additional training period by the use of new data. Backpropagation denotes a widely known, supervised learning technique which requires the repeated presentation of a set of training instances. Recruitment learning denotes a technique which converts network units from a pool of free units into units which carry meaningful information, and can be used for both instruction-based and similarity-based learning. It will be shown that a learning technique which makes use of structured knowledge (i.e. recruitment learning), re-learns and modifies a connectionist representation faster than backpropagation. (Copyright (c) GMD 1990.)

• Research Organization: Gesellschaft fuer Mathematik und Datenverarbeitung mbH Bonn, St. Augustin (Germany). Inst. fuer Angewandte Informationstechnik
• OSTI ID: 5447719
• Report Number(s): PB-91-192203/XAB; GMD--457
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ARTIFICIAL INTELLIGENCE
DATA PROCESSING
DISTRIBUTED DATA PROCESSING
KNOWLEDGE BASE
LEARNING
NEURAL NETWORKS
PARALLEL PROCESSING
PROCESSING
PROGRAMMING
TECHNOLOGY ASSESSMENT