Training Recurrent Neural Networks with Temporal Input Encodings

Abstract

| We investigate the learning of de-terministic nite-state automata (DFA's) with recurrent networks with a single input neu-ron, where each input symbol is represented as a temporal pattern and strings as sequences of temporal patterns. We empirically demonstrate that obvious temporal encodings can make learning very diicult or even impossible. Based on… (More)

Topics

1 Figure or Table

Cite this paper

@inproceedings{Omlin1994TrainingRN, title={Training Recurrent Neural Networks with Temporal Input Encodings}, author={C. W. Omlin and Cicely Giles and B. G. Horne and Laurens R. Leerink and T. Lin}, year={1994} }