Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM

DOI10.1162/089976602320263980zbMATH Open1010.68857DBLPjournals/neco/SchmidhuberGE02OpenAlexW2154039517WikidataQ52011065 ScholiaQ52011065MaRDI QIDQ3149504FDOQ3149504

Authors: Jürgen Schmidhuber, Felix Gers, Douglas Eck 

Publication date: 13 May 2003

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/089976602320263980

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Computing methodologies and applications (68U99)

Cites Work

• Simple recurrent networks learn context-free and context-sensitive languages by counting.

Cited In (6)

• Learning to imitate stochastic time series in a compositional way by chaos
• Training Recurrent Networks by Evolino
• Hierarchical linear dynamical systems for unsupervised musical note recognition
• LSTM
• A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance
• Stack-like and queue-like dynamics in recurrent neural networks

This page was built for publication: Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3149504)