LSTM: A Search Space Odyssey

@article{Greff2017LSTMAS,
  title={LSTM: A Search Space Odyssey},
  author={Klaus Greff and R. Srivastava and J. Koutn{\'i}k and Bas R. Steunebrink and J. Schmidhuber},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2017},
  volume={28},
  pages={2222-2232}
}
Several variants of the long short-term memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative… Expand
2,526 Citations
Performance of Three Slim Variants of The Long Short-Term Memory (LSTM) Layer
  • Daniel Kent, F. Salem
  • Computer Science
  • 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)
  • 2019
  • 14
  • Highly Influenced
  • PDF
Restricted Recurrent Neural Networks
  • 6
  • PDF
Learning compact recurrent neural networks
  • 72
  • PDF
From Nodes to Networks: Evolving Recurrent Neural Networks
  • 38
  • PDF
An Empirical Exploration of Recurrent Network Architectures
  • 1,194
  • PDF
A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
  • 101
Investigating gated recurrent neural networks for acoustic modeling
  • Y. Zhao, J. Li, S. Xu, Bo Xu
  • Computer Science
  • 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)
  • 2016
  • 6
A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition
  • 126
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
Long short-term memory recurrent neural network architectures for large scale acoustic modeling
  • 1,671
  • PDF
Training Recurrent Networks by Evolino
  • 233
  • PDF
Speech recognition with deep recurrent neural networks
  • 5,873
  • PDF
Learning to Forget: Continual Prediction with LSTM
  • 2,181
Framewise phoneme classification with bidirectional LSTM and other neural network architectures
  • 2,576
  • Highly Influential
  • PDF
Dropout Improves Recurrent Neural Networks for Handwriting Recognition
  • 419
  • PDF
Multi-resolution linear prediction based features for audio onset detection with bidirectional LSTM neural networks
  • 66
  • PDF
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
  • 5,558
  • PDF
Dynamic Cortex Memory: Enhancing Recurrent Neural Networks for Gradient-Based Sequence Learning
  • 19
...
1
2
3
4
5
...