User Tools

Site Tools


recurrent_neural_network

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
recurrent_neural_network [2019/04/11 16:35]
burkov
recurrent_neural_network [2020/10/22 02:24]
198.84.252.54
Line 7: Line 7:
 ===== Recommended Reading ===== ===== Recommended Reading =====
  
 +  * [[https://​www.dropbox.com/​s/​ouj8ddydc77tewo/​ExtendedChapter6.pdf?​dl=0|An extended version of Chapter 6 with RNN unfolding and bidirectional RNN]]
   * [[http://​karpathy.github.io/​2015/​05/​21/​rnn-effectiveness/​|The Unreasonable Effectiveness of Recurrent Neural Networks]] by Andrej Karpathy (2015)   * [[http://​karpathy.github.io/​2015/​05/​21/​rnn-effectiveness/​|The Unreasonable Effectiveness of Recurrent Neural Networks]] by Andrej Karpathy (2015)
   * [[https://​towardsdatascience.com/​recurrent-neural-networks-and-lstm-4b601dd822a5|Recurrent Neural Networks and LSTM]] by Niklas Donges (2018)   * [[https://​towardsdatascience.com/​recurrent-neural-networks-and-lstm-4b601dd822a5|Recurrent Neural Networks and LSTM]] by Niklas Donges (2018)
Line 15: Line 16:
   * [[http://​www.wildml.com/​2015/​10/​recurrent-neural-network-tutorial-part-4-implementing-a-grulstm-rnn-with-python-and-theano/​|Implementing a GRU/LSTM RNN with Python and Theano]] by Denny Britz (2015)   * [[http://​www.wildml.com/​2015/​10/​recurrent-neural-network-tutorial-part-4-implementing-a-grulstm-rnn-with-python-and-theano/​|Implementing a GRU/LSTM RNN with Python and Theano]] by Denny Britz (2015)
   * [[https://​arxiv.org/​abs/​1701.03452|Simplified Minimal Gated Unit Variations for Recurrent Neural Networks]] by Joel Heck and Fathi Salem (2017)   * [[https://​arxiv.org/​abs/​1701.03452|Simplified Minimal Gated Unit Variations for Recurrent Neural Networks]] by Joel Heck and Fathi Salem (2017)
 +  * [[https://​arxiv.org/​abs/​1706.03762|Attention Is All You Need]] by Vaswani et al. (2017), a state-of-the-art sequence-to-sequence model, plus an [[http://​jalammar.github.io/​illustrated-transformer/​|illustrated guide]]