Deep Learning Reading Club

Understanding a research paper can be a time consuming endeavour. With the massive output of deep learning research it can be difficult to keep up with all of the most exciting ideas. The purpose of this club is help researchers understand and discuss exciting deep learning papers in a collaborative setting.

Current Meetings

Paper Slides Presenter

Past Meetings

Paper Slides Presenter
GANSpace: Discovering Interpretable GAN Controls Slides Nolan Dey
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent 8 min Concept Overview PDF Notes YouTube Playlist Mihai Nica
Neural Tangent Kernel: Convergence and Generalization in Neural Networks Slides Nolan Dey
What can neural networks reason about? Slides Shashank Shekhar
Dynamic Routing Between Capsules Slides Brent Komer
LambdaNetworks: Modeling long-range Interactions without Attention Slides Salman Khan
Neural Ordinary Differential Equations Slides Mohammed Adnan
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Slides Parsa Torabian
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks Slides Nolan Dey
Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness Slides Salman Khan
Network Dissection: Quantifying Interpretability of Deep Visual Representations Slides Nolan Dey
Evolving Neural Networks Through Augmenting Topologies Slides Ramashish Gaurav
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? Slides Mohammed Adnan
Semantic Pointer Architecture Slides Xueyang Yao
Semi-Supervised Classification with Graph Convolutional Networks Slides Nolan Dey
BRUNO: A Deep Recurrent Model for Exchangeable Data Slides Mohammed Adnan
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Slides Nolan Dey