Holographic Reduced Representations: Convolution Algebra for Compositional Distributed Representations
Proceedings of the Twelfth International Joint Conference on Artificial Intelligence. Architectures & Languages. Pages 30-34.
Abstract
A solution to the problem of representing compositional structure using distributed representations is described. The method uses circular convolution to associate items, which are represented by vectors . Arbitrary variable bindings, short sequences of various lengths, frames, and reduced representations can be compressed into a fixed 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 reconstructive properties.
@inproceedings{ijcai1991p5,
title = {Holographic Reduced Representations: Convolution Algebra for Compositional Distributed Representations},
author = {Plate, Tony},
booktitle = {Proceedings of the Twelfth International Joint Conference on
Artificial Intelligence, {IJCAI-91}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {John Mylopoulos and Ray Reiter},
pages = {30--34},
year = {1991},
month = {8},
note = {Architectures & Languages},
url = {https://ijcai.org/proceedings/1991/5},
}
TY - CPAPER TI - Holographic Reduced Representations: Convolution Algebra for Compositional Distributed Representations AU - Plate, Tony T2 - Proceedings of the Twelfth International Joint Conference on Artificial Intelligence, IJCAI-91 PB - International Joint Conferences on Artificial Intelligence PY - 1991 SP - 30 EP - 34 UR - https://ijcai.org/proceedings/1991/5 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
