Consistency and Generalization in Incrementally Trained Connectionist Networks

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 hamming 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.