Corpus ID: 7823468

Grid Long Short-Term Memory

@article{Kalchbrenner2016GridLS,
  title={Grid Long Short-Term Memory},
  author={Nal Kalchbrenner and Ivo Danihelka and A. Graves},
  journal={CoRR},
  year={2016},
  volume={abs/1507.01526}
}
This paper introduces Grid Long Short-Term Memory, a network of LSTM cells arranged in a multidimensional grid that can be applied to vectors, sequences or higher dimensional data such as images. [...] Key Method We apply the model to algorithmic tasks such as 15-digit integer addition and sequence memorization, where it is able to significantly outperform the standard LSTM. We then give results for two empirical tasks. We find that 2D Grid LSTM achieves 1.47 bits per character on the Wikipedia character…Expand
284 Citations
A prioritized grid long short-term memory RNN for speech recognition
  • 21
  • Highly Influenced
  • PDF
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
  • 156
  • PDF
Persistent Hidden States and Nonlinear Transformation for Long Short-Term Memory
  • 4
  • PDF
Reducing the Computational Complexity of Two-Dimensional LSTMs
  • 10
Highway long short-term memory RNNS for distant speech recognition
  • 231
  • PDF
Recurrent Highway Networks
  • 320
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
Sequence to Sequence Learning with Neural Networks
  • 12,035
  • Highly Influential
  • PDF
Long Short-Term Memory
  • 37,267
  • PDF
LSTM: A Search Space Odyssey
  • 2,507
  • PDF
Learning to Execute
  • 410
  • PDF
Speech recognition with deep recurrent neural networks
  • 5,829
  • PDF
Gated Feedback Recurrent Neural Networks
  • 552
  • PDF
Network In Network
  • 3,394
  • PDF
Show and tell: A neural image caption generator
  • 3,764
  • PDF
Generating Sequences With Recurrent Neural Networks
  • 2,643
  • PDF
...
1
2
3
4
5
...