Textbook of AI

Further reading

• Goodfellow, Bengio and Courville (2016), Deep Learning, Chapter 10, recurrent and recursive networks.
• Jurafsky and Martin (forthcoming third edition), Speech and Language Processing, chapters on language models, embeddings, RNNs, and attention.
• Olah (2015), "Understanding LSTM Networks", the canonical visual exposition.
• Karpathy (2015), "The Unreasonable Effectiveness of Recurrent Neural Networks", the min-char-rnn blog post.
• Bahdanau, Cho and Bengio (2015) 2014, the original attention paper.
• Sutskever, Vinyals and Le 2014, sequence-to-sequence learning.
• Hochreiter and Schmidhuber 1997, the LSTM paper.
• Mikolov et al. 2013, Pennington et al. 2014, Bojanowski et al. 2017, the word-embedding triumvirate.
• Sennrich, Haddow and Birch 2016, BPE for NMT.
• Graves et al. 2006, Connectionist Temporal Classification.
• Holtzman et al. 2019, nucleus sampling.
• Vaswani et al. 2017, Attention Is All You Need (preview of Chapter 13).