A general method, the tensor product representation, is described for the distributed representation of value/variable bindings. The method allows the fully distributed representation of symbolic structures: the roles in the structures, as well as the fillers for those roles, can be arbitrarily non-local. Fully and partially localized special cases reduce to existing cases of connectionist representations of structured data; the tensor product representation generalizes these and the few existing examples of fully distributed representations of structures. The representation saturates gracefully as larger structures are represented; it permits recursive construction of complex representations from simpler ones; it respects the independence of the capacities to generate and maintain multiple bindings in parallel; it extends naturally to continuous structures and continuous representational patterns; it permits values to also serve as variables; it enables analysis of the interference of symbolic structures stored in associative memories; and it leads to characterization of optimal distributed representations of roles and a recirculation algorithm for learning them.
[1]
Geoffrey E. Hinton,et al.
Parallel Models of Associative Memory
,
1989
.
[2]
James L. McClelland,et al.
Parallel Distributed Processing: Explorations in the Microstructure of Cognition : Psychological and Biological Models
,
1986
.
[3]
James L. McClelland,et al.
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
,
1986
.
[4]
Mark Derthick.
Counterfactual Reasoning with Direct Models
,
1987,
AAAI.
[5]
Geoffrey E. Hinton.
A Parallel Computation that Assigns Canonical Object-Based Frames of Reference
,
1981,
IJCAI.
[6]
Lewis M. Norton,et al.
Proceedings of the International Joint Conference on Artificial Intelligence : May 7-9, 1969, Washington, D.C.
,
1969
.