Holographic Reduced Representations: Convolution Algebra for Compositional Distributed Representations

A solution to the problem of representing compo-sitional structure using distributed representations is described. The method uses circular convolution to associate items, which are represented by v ec-tors. Arbitrary variable bindings, short sequences of various lengths, frames, and reduced representations can be compressed into a xed width vector. These representations are items in their own right, and can be used in constructing compositional structures. The noisy reconstructions given by convolution memories can be cleaned up by using a separate associative memory that has good recon-structive properties.

[1]  Janet Metcalfe,et al.  A composite holographic associative recall model , 1982 .

[2]  J. Eich.  A composite holographic associative recall model. , 1982 .

[3]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[4]  B. Murdock.  A Theory for the Storage and Retrieval of Item and Associative Information. , 1982 .

[5]  Bennet B. Murdock,et al.  A distributed memory model for serial-order information. , 1983 .

[6]  Jon M. Slack.  A Parsing Architecture Based On Distributed Memory Machines , 1984, COLING.

[7]  Ray Pike,et al.  Comparison of convolution and matrix distributed memory systems for associative recall and recognition , 1984 .

[8]  Geoffrey E. Hinton,et al.  Symbols Among the Neurons: Details of a Connectionist Inference Architecture , 1985, IJCAI.

[9]  David S. Touretzky,et al.  A distributed connectionist representation for concept structures , 1987 .

[10]  J. Fodor,et al.  Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.

[11]  Pentti Kanerva,et al.  Sparse Distributed Memory , 1988 .

[12]  Paul Smolensky,et al.  Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1990, Artif. Intell..

[13]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[14]  Geoffrey E. Hinton.  Mapping Part-Whole Hierarchies into Connectionist Networks , 1990, Artif. Intell..

[15]  Geoffrey E. Hinton.  Preface to the Special Issue on Connectionist Symbol Processing , 1990 .