Week 1: Recurrent Neural Networks

Week 2: Natural Language Processing & Word Embeddings

Week 3: Sequence Models & Attention Mechanism

Week 4: Transformer Network

References

Week 1:

• Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy (GitHub: karpathy)
• The Unreasonable Effectiveness of Recurrent Neural Networks (Andrej Karpathy blog, 2015)
• deepjazz (GitHub: jisungk)
• Learning Jazz Grammars (Gillick, Tang & Keller, 2010)
• A Grammatical Approach to Automatic Improvisation (Keller & Morrison, 2007)
• Surprising Harmonies (Pachet, 1999)

Week 2:

• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (Bolukbasi, Chang, Zou, Saligrama & Kalai, 2016)
• GloVe: Global Vectors for Word Representation (Pennington, Socher & Manning, 2014)
• Woebot.

Week 4:

• [Natural Language Processing Specialization](https://www.coursera.org/specializations/natural-language-processing?) (by DeepLearning.AI)
• Attention Is All You Need (Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser & Polosukhin, 2017)