Schedule (tentative)

• Borman, The EM algorithm (A short tutorial)
• Neal and Hinton, A view of the EM algorithm

• PRML, Chapter 10.1-10.3
• Deep Learning book, Chap 20.10.3
• Kingma and Welling, 2014, Variational Autoencoders

• Lecun and Misra, (Blog) Self-supervised learning: The dark matter of intelligence
• Devlin et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

• Ting et al. A Simple Framework for Contrastive Learning of Visual Representations
• Oord et al. Representation Learning with Contrastive Predictive Coding
• Chris Dyer Notes on Noise Contrastive Estimation and Negative Sampling

HW1 out

• Shorten and Khoshgoftaar A survey on Image Data Augmentation for Deep Learning
• Chen et al. An Empirical Survey of Data Augmentation for Limited Data Learning in NLP
• Hu et al. Learning Data Manipulation for Augmentation and Weighting

Project proposal due

• Bengio et al. Curriculum Learning
• Dan Roth Incidental Supervision: Moving beyond Supervised Learning
• Ratner et al. Snorkel: rapid training data creation with weak supervision

• Hu and Xing, Panoramic learning

• PRML, Appendix D. Calculus of Variations

HW1 due, HW2 out

• Goodfellow et al., Generative Adversarial Nets
• Zhu et al., Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Paper presentation starts

• Hu et al., Harnessing Deep Neural Networks with Logic Rules

• Lilian Weng, A (Long) Peek into Reinforcement Learning

HW2 due

• Sutton, Barto, Reinforcement Learning, An Introduction, Chapter 13.

• Lilian Weng, Meta-Learning: Learning to Learn Fast

Project mid-term report due

• Hu et al., Toward Controlled Generation of Text

• Guo et al., Text Generation with Efficient (Soft) Q-Learning

Project final report due