Readings

Roger’s Course Notes:

• Distributed Representations
• Automatic Differentiation

Autograd tutorial

Autodidact

Recommended papers (optional):

• Y. Bengio, R. Ducharme, P. Vincent, and C. Jauvin. A neural probabilistic language model. JMLR 2003.
• J. Pennington, R. Socher, and C. Manning. GloVe: Global vectors for word representation. EMNLP 2014.
• D. Maclaurin, D. Duvenaud, and R. P. Adams. Gradient-based hyperparameter optimization through reversible learning. ICML 2015.

Alice’s Slides

w03_1_automatic_differentiation_slides.pdf

w03_1_automatic_differentiation_complete.pdf

w03_2_distributed_representations_slides.pdf

w03_2_distributed_representations_complete.pdf

w03_3_optimization_slides.pdf

w03_3_optimization_complete.pdf

Roger’s Slides:

lec03.pdf

Nikita’s Slides: