Recursive hetero-associative memories for translation

Lecture notes in computer sciencePublished 1 January 1997

Mikel L. Forcada, Ramón P. Ñeco

DOI10.1007/bfb0032504

Source URL

Citations84

SJR quartileQ2

SJR score0.35

SNIP0.55

TL;DR

A modification of Pollack's RAAM is presented, called a Recursive Hetero-Associative Memory (RHAM), and it is shown that it is capable of learning simple translation tasks, by building a state-Space representation of each input string and unfolding it to obtain the corresponding output string.

Abstract

This paper presents a modification of Pollack's RAAM (Recursive Auto-Associative Memory), called a Recursive Hetero-Associative Memory (RHAM), and shows that it is capable of learning simple translation tasks, by building a state-Space representation of each input string and unfolding it to obtain the corresponding output string. RHAM-based translators are computationally more powerful and easier to train than their corresponding double-RAAM counterparts in the literature.

Keywords

Computer Science

Learning Internal Representations by Error Propagation

16,235 Citations1985David E. Rumelhart, Geoffrey E. Hinton +1 more

The MIT Press eBooksParallel Distributed Processing

15,227 Citations1986David E. Rumelhart, James L. McClelland +1 more

Mathematics and Computers in SimulationIntroduction to automata theory, languages and computation

10,827 Citations1981

Neural ComputationA Learning Algorithm for Continually Running Fully Recurrent Neural Networks

4,451 Citations1989Ronald J. Williams, David Zipser

The exact form of a gradient-following learning algorithm for completely recurrent networks running in continually sampled time is derived and used as the basis for practical algorithms for temporal supervised learning tasks.

Artificial IntelligenceRecursive distributed representations

866 Citations1990Jordan Pollack

This paper presents a connectionist architecture which automatically develops compact distributed representations for variable-sized recursive data structures, as well as efficient accessing mechanisms for them.

Syntactic Transformations on Distributed Representations

185 Citations1992David J. Chalmers

This paper explores the possibility of moving beyond implementation by exploiting holistic structure-sensitive operations on distributed representations using Pollack’s Recursive Auto-Associative Memory, demonstrating that the implicit structure present in these representations can be used for a kind of structure- sensitive processing unique to the connectionist domain.

Connection ScienceSyntactic Transformations on Distributed Representations

140 Citations1990David J. Chalmers

Neural ComputationAlopex: A Correlation-Based Learning Algorithm for Feedforward and Recurrent Neural Networks

113 Citations1994K. P. Unnikrishnan, K. Venugopal

This paper presents a learning algorithm for neural networks, called Alopex, which uses local correlations between changes in individual weights and changes in the global error measure, and shows that learning times are comparable to those for standard gradient descent methods.

Connection ScienceLearning Recursive Distributed Representations for Holistic Computation

76 Citations1991Lonnie Chrisman

Two possible forms of holistic inference, transformational inference and confluent inference, are identified and compared and a dual-ported RAAM architecture based on Pollack's Recursive Auto-Associative Memory is implemented and demonstrated in the domain of Natural Language translation.

View PDF