UPDF AI

Recursive Hetero-associative Memories for Translation

M. Forcada,R. Ñeco

1997 · DOI: 10.1007/BFb0032504
International Work-Conference on Artificial and Natural Neural Networks · 73 Citations

TLDR

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.