Keywords

connectionist networks, incremental rule learning, example learning, generalization

Abstract

This paper discusses aspects of consistency and generalization in connectionist networks which learn through incremental training by examples or rules. Differences between training set learning and incremental rule or example learning are presented. Generalization, the ability to output reasonable mappings when presented with novel input patterns, is discussed in light of the above learning methods. In particular, the contrast between humming distance generalization and generalizing by high order combinations of critical variables is overviewed. Examples of detailed rules for an incremental learning model are presented for both consistency and generalization constraints.

Original Publication Citation

Martinez, T. R., "Consistency and Generalization of Incrementally Trained Connectionist Models", Proceedings of the International Symposium on Circuits and Systems, pp. 76-79, 199.

Document Type

Peer-Reviewed Article

Publication Date

1990-05-03

Permanent URL

http://hdl.lib.byu.edu/1877/2417

Publisher

IEEE

Language

English

College

Physical and Mathematical Sciences

Department

Computer Science

Share

COinS