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.
Keywords
Convolution (computer science)Simple (philosophy)Content-addressable memoryComputer scienceAssociative propertyFrame (networking)AlgorithmHolographyContent-addressable storageTheoretical computer scienceArtificial intelligencePattern recognition (psychology)MathematicsArtificial neural networkPure mathematics
Affiliated Institutions
Related Publications
Normalized and differential convolution
It is shown how false operator responses due to missing or uncertain data can be significantly reduced or eliminated. It is shown how operators having a higher degree of selecti...
Session-Based Recommendation with Graph Neural Networks
The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representa...
Neural networks and physical systems with emergent collective computational abilities.
Computational properties of use of biological organisms or to the construction of computers can emerge as collective properties of systems having a large number of simple equiva...
Perceptual symbol systems
Prior to the twentieth century, theories of knowledge were inherently perceptual. Since then, developments in logic, statistics, and programming languages have inspired amodal t...
Publication Info
- Year
- 1995
- Type
- article
- Volume
- 6
- Issue
- 3
- Pages
- 623-641
- Citations
- 652
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
652
OpenAlex
Cite This
Tony Plate
(1995).
Holographic reduced representations.
IEEE Transactions on Neural Networks
, 6
(3)
, 623-641.
https://doi.org/10.1109/72.377968
Identifiers
- DOI
- 10.1109/72.377968