Recursive distributed representations

DMCA

Recursive distributed representations (1990)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Jordan B. Pollack

Venue:	Artificial Intelligence
Citations:	414 - 9 self

BibTeX

@ARTICLE{Pollack90recursivedistributed,
    author = {Jordan B. Pollack},
    title = {Recursive distributed representations},
    journal = {Artificial Intelligence},
    year = {1990},
    volume = {46},
    pages = {77--105}
}

OpenURL

Abstract

A long-standing difficulty for connectionist modeling has been how to represent variable-sized recursive data structures, such as trees and lists, in fixed-width patterns. This paper presents a connectionist architecture which automatically develops compact distributed representations for such compositional structures, as well as efficient accessing mechanisms for them. Patterns which stand for the internal nodes of fixed-valence trees are devised through the recursive use of back-propagation on three-layer autoassociative encoder networks. The resulting representations are novel, in that they combine apparently immiscible aspects of features, pointers, and symbol structures. They form a bridge between the data structures necessary for high-level cognitive tasks and the associative, pattern recognition machinery provided by neural networks. 2 J. B. Pollack 1.

Keyphrases

recursive use data structure high-level cognitive task connectionist architecture resulting representation variable-sized recursive data structure three-layer autoassociative encoder network internal node compositional structure long-standing difficulty connectionist modeling compact distributed representation fixed-width pattern fixed-valence tree symbol structure neural network pattern recognition machinery immiscible aspect

DMCA