Autumn 2020 Discussions

We conduct two discussions every week where we dicuss the basic concepts and recent advancements in the field of Deep Learning.

Basic Discussions

We discuss a few fundamental concepts on Wednesdays.

Date Topic Resources
04-08-2020 Linear Algebra Slides
11-08-2020 Probability Slides
19-08-2020 Neural Networks and CNNs Slides
26-08-2020 Basic CNN architectures Slides
02-09-2020 RNNs Slides
09-09-2020 VAE Slides
16-09-2020 GANs Slides
23-09-2020 Embeddings Slides
30-09-2020 Attention and Transformer Slides
07-10-2020 ELMo and BERT Slides
14-10-2020 RL-I: MDPs, Bellman Equations Slides-A Slides-B
11-11-2020 Graph Neural Networks Slides

Advanced Discussions

We discuss the latest papers published in top tier conferences on Saturdays.

Paper 1
Paper 2
01-08-2020 Reinforced active learning for image segmentation Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
08-08-2020 Towards Recognizing Unseen Categories in Unseen Domains Neural Arithmetic Units
29-08-2020 Learning Memory Access Patterns Equalization Loss for Long-Tailed Object Recognition
05-09-2020 PnPNet: End-to-End Perception and Prediction with Tracking in the Loop CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
26-09-2020 Adversarial Continual Learning Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
10-10-2020 Implicit Latent Variable Model for Scene-Consistent Motion Forecasting Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
31-10-2020 Causal Discovery with Reinforcement Learning What Should Not Be Contrastive in Contrastive Learning
07-11-2020 Dual Super-Resolution Learning for Semantic Segmentation Neural Architecture Search without Training Learning
28-11-2020 Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Vision and Language Group
Vision and Language Group

Deep Learning Research Group