论文信息 - Recursive Hetero-associative Memories for Translation

Recursive Hetero-associative Memories for Translation

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.

Mikel L. Forcada | Ramón P. Ñeco | M. Forcada | R. Ñeco

[1] Peter C. Chapin. Formal languages I , 1973, CSC '73.

[2] Jeffrey D. Ullman,et al. Introduction to Automata Theory, Languages and Computation , 1979 .

[3] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[4] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[5] Ronald J. Williams,et al. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[6] Jordan B. Pollack,et al. Recursive Distributed Representations , 1990, Artif. Intell..

[7] David J. Chalmers,et al. Syntactic Transformations on Distributed Representations , 1990 .

[8] Lonnie Chrisman,et al. Learning Recursive Distributed Representations for Holistic Computation , 1991 .

[9] K. P. Unnikrishnan,et al. Alopex: A Correlation-Based Learning Algorithm for Feedforward and Recurrent Neural Networks , 1994, Neural Computation.