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

@article{Schmidhuber2002LearningNL,
  title={Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM},
  author={J. Schmidhuber and F. Gers and D. Eck},
  journal={Neural Computation},
  year={2002},
  volume={14},
  pages={2039-2041}
}
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. 
72 Citations
Improving procedures for evaluation of connectionist context-free language predictors
  • 6
  • Highly Influenced
Recurrent Residual Network
  • 2017
  • PDF
CU-NLP at SemEval-2016 Task 8: AMR Parsing using LSTM-based Recurrent Neural Networks
  • 13
  • PDF
Incremental Learning for RNNs: How Does it Affect Performance and Hidden Unit Activation?
  • PDF
Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks
  • 21
  • PDF
Improved access to sequential motifs: a note on the architectural bias of recurrent networks
  • 10
Subregular Complexity and Deep Learning
  • 22
  • PDF
A Connectionist Approach to Learn Marathi Language
  • S. R. Kolhe, B. Pawar
  • Computer Science
  • 2008 First International Conference on Emerging Trends in Engineering and Technology
  • 2008
State-Regularized Recurrent Neural Networks
  • 14
  • PDF
Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages
  • 16
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 11 REFERENCES
LSTM recurrent networks learn simple context-free and context-sensitive languages
  • 495
  • PDF
Improving procedures for evaluation of connectionist context-free language predictors
  • 6
Long Short-Term Memory Learns Context Free and Context Sensitive Languages
  • 24
  • Highly Influential
Simple Recurrent Networks Learn Context-Free and Context-Sensitive Languages by Counting
  • 100
Context-free and context-sensitive dynamics in recurrent neural networks
  • 72
  • PDF
Long Short-Term Memory
  • 38,198
  • PDF
Finding Structure in Time
  • 9,061
  • PDF
Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies
  • 1,343
  • PDF
Untersuchungen zu dynamischen neuronalen Netzen
  • 531
  • Highly Influential
Untersuchungen zu dynamischen neuronalen Netzen. Diploma thesis, Institut für Informatik, Lehrstuhl Prof
  • Untersuchungen zu dynamischen neuronalen Netzen. Diploma thesis, Institut für Informatik, Lehrstuhl Prof
  • 1991
...
1
2
...