2022-1 Deep Learning and Applications
In this lecture, we will be learning about two different topics in deep learning: self-supervised learning (SSL) and generative models. For SSL, 50 papers were curated in computer vision, natural language processing, and robotics.
Syllabus
- Week 1 (3/7): Historical Review
- Week 2 (3/15): Self-supervised learning 1 (Jigsaw, BiGAN, RotNet, Auto-Encoding Transform, DeepCluster, Single Image SSL)
- Week 3 (3/22): Self-supervised learning 2 (DrLIM, MoCo, SimCLR, SimCLRv2)
- Week 4 (3/29): Self-supervised learning 3 (NLP Domain)
- Week 5 (4/5): Self-supervised learning 4 (Robotics Domain)
- Week 6:(4/12) Invited Talk
- Week 7-9: Interlim Presentations
- Week 10 (5/10): Generative Model 1 (AR model, ML learning)
- Week 11 (5/17): Generative Model 2 (VAE, WAE, GAN, Flow-based models)
- Week 12 (5/24): Generative Model 3 (DDPM)
- Week 13 (5/31): Generative Model 4 (More diffusion-based + score-based models)
- Week 14-16: Final Presentations