Rule Representations in a Connectionist Chunker

Part of Advances in Neural Information Processing Systems 2 (NIPS 1989)

Authors

David Touretzky, Gillette Elvgreen

Abstract

We present two connectionist architectures for chunking of symbolic rewrite rules. One uses backpropagation learning, the other competitive learning. Although they were developed for chunking the same sorts of rules, the two differ in their representational abilities and learning behaviors.