/2022-1-deep-learning-applications

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, Contrastive Predictive Coding, SimCLR, MoCo, BYOL, SimCLRv2, SwAV, Barlow Twins)
  • 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

Paper Lists

  • Jigsaw: "Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles," 2017
  • BiGAN: "ADVERSARIAL FEATURE LEARNING," 2017
  • RotNet: "UNSUPERVISED REPRESENTATION LEARNING BY PREDICTING IMAGE ROTATIONS," 2018
  • Auto-Encoding Transform: "AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data," 2019
  • DeepCluster: "Deep Clustering for Unsupervised Learning of Visual Features," 2019
  • Single Image SSL: "A CRITICAL ANALYSIS OF SELF-SUPERVISION, WHAT WE CAN LEARN FROM A SINGLE IMAGE," 2020
  • DrLIM: "Dimensionality Reduction by Learning an Invariant Mapping," 2006
  • Contrastive Predictive Coding: "Representation Learning with Contrastive Predictive Coding," 2019
  • SimCLR: "A Simple Framework for Contrastive Learning of Visual Representations," 2020
  • MoCo: "Momentum Contrast for Unsupervised Visual Representation Learning," 2020
  • BYOL: "Bootstrap Your Own Latent A New Approach to Self-Supervised Learning," 2020
  • SimCLRv2: "Big Self-Supervised Models are Strong Semi-Supervised Learners," 2020
  • SwAV: "Unsupervised Learning of Visual Features by Contrasting Cluster Assignments," 2021
  • Barlow Twins: "Barlow Twins: Self-Supervised Learning via Redundancy Reduction," 2021
This syllabus is subject to further change or revision, as needed, to best realize the educational goals of the course.