Holographic reduced representations
Plate, T.A.
British Columbia Cancer Res. Centre, Vancouver, BC ;
This paper appears in: Neural Networks, IEEE Transactions on
Publication Date: May 1995
Volume: 6,
Issue: 3
On page(s): 623-641
ISSN: 1045-9227
References Cited: 38
CODEN: ITNNEP
INSPEC Accession Number: 4960403
Digital Object Identifier: 10.1109/72.377968
Current Version Published: 2002-08-06
Abstract
Associative memories are conventionally used to represent data
with very simple structure: sets of pairs of vectors. This paper
describes a method for representing more complex compositional structure
in distributed representations. The method uses circular convolution to
associate items, which are represented by vectors. Arbitrary variable
bindings, short sequences of various lengths, simple frame-like
structures, and reduced representations can be represented in a fixed
width vector. These representations are items in their own right and can
be used in constructing compositional structures. The noisy
reconstructions extracted from convolution memories can be cleaned up by
using a separate associative memory that has good reconstructive
properties
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
