Learning Recursive Distributed Representations for Holistic Computation
- 1 January 1991
- journal article
- Published by Taylor & Francis in Connection Science
- Vol. 3 (4) , 345-366
- https://doi.org/10.1080/09540099108946592
Abstract
A number of connectionist models capable of representing data with compositional structurehave recently appeared. These new models suggest the intriguing possibility of performingholistic structure-sensitive computations with distributed representations. Two possibleforms of holistic inference, transformational inference and confluent inference, are identifiedand compared. Transformational inference was successfully demonstrated in [Chalmers,1990]; however, since the pure transformational...Keywords
This publication has 15 references indexed in Scilit:
- Learning Recursive Distributed Representations for Holistic ComputationConnection Science, 1991
- Mapping part-whole hierarchies into connectionist networksArtificial Intelligence, 1990
- BoltzCONS: Dynamic symbol structures in a connectionist networkArtificial Intelligence, 1990
- Tensor product variable binding and the representation of symbolic structures in connectionist systemsArtificial Intelligence, 1990
- Recursive distributed representationsArtificial Intelligence, 1990
- Learning and applying contextual constraints in sentence comprehensionArtificial Intelligence, 1990
- Compositionality: A connectionist variation on a classical themeCognitive Science, 1990
- Learning Distributed Representations of Conceptual Knowledge and their Application to Script-based Story ProcessingConnection Science, 1990
- Syntactic Transformations on Distributed RepresentationsConnection Science, 1990
- Connectionism and cognitive architecture: A critical analysisCognition, 1988