Learning nonregular languages: a comparison of simple recurrent networks and LSTM

Authors:
J. Schmidhuber;F. Gers;D. Eck
Affiliations:
Instituto Dalle Molle di Studi sull'Intelligenza Artificiale, 6928 Manno-Lugano, Switzerland;Instituto Dalle Molle di Studi sull'Intelligenza Artificiale, 6928 Manno-Lugano, Switzerland;Instituto Dalle Molle di Studi sull'Intelligenza Artificiale, 6928 Manno-Lugano, Switzerland
Venue:
Neural Computation
Year:
2002

Citing 3
Cited 4

Long short-term memory

Neural Computation
Simple Recurrent Networks Learn Context-Free and Context-Sensitive Languages by Counting

Neural Computation
LSTM recurrent networks learn simple context-free and context-sensitive languages

IEEE Transactions on Neural Networks

Training Recurrent Networks by Evolino

Neural Computation
A Characterization of Simple Recurrent Neural Networks with Two Hidden Units as a Language Recognizer

Neural Information Processing
A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance

Neural Networks
Learning to imitate stochastic time series in a compositional way by chaos

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In response to Rodriguez's recent article (2001), we compare the performance of simple recurrent nets and long short-term memory recurrent nets on context-free and context-sensitive languages.