| Sun Sep 05 |
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks , Saxe, McClelland, Ganguli; 2013 |
Coding |
| Fri Sep 10 |
Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates , Smith, Topin; 2017 |
Review both summaries |
| Wed Sep 15 |
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks , Salimans, Kingma; 2016 |
Draft Summary |
| Sun Sep 19 |
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks , Salimans, Kingma; 2016 |
Final Summary |
| Wed Sep 22 |
End-To-End Memory Networks , Sukhbaatar, Szlam, Weston, Fergus; 2015 |
Draft Summary |
| Sun Sep 26 |
End-To-End Memory Networks , Sukhbaatar, Szlam, Weston, Fergus; 2015 |
Final Summary |
| Sun Oct 03 |
Reformer: The Efficient Transformer , Kitaev, Kaiser, Levskaya; 2020 |
Coding |
| Fri Oct 08 |
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions , Wang, Xie, Li, Fan, Song, Liang, Lu, Luo, Shao; 2021 |
Review both summaries |
| Wed Oct 13 |
Implicit Geometric Regularization for Learning Shapes , Gropp, Yariv, Haim, Atzmon, Lipman; 2020 |
Draft Summary |
| Sun Oct 17 |
Implicit Geometric Regularization for Learning Shapes , Gropp, Yariv, Haim, Atzmon, Lipman; 2020 |
Final Summary |
| Wed Oct 20 |
Cascade R-CNN: Delving into High Quality Object Detection , Cai, Vasconcelos; 2017 |
Draft Summary |
| Sun Oct 24 |
Cascade R-CNN: Delving into High Quality Object Detection , Cai, Vasconcelos; 2017 |
Final Summary |
| Sun Oct 31 |
PointCNN: Convolution On $\mathcal{X}$-Transformed Points , Li, Bu, Sun, Wu, Di, Chen; 2018 |
Coding |
| Fri Nov 05 |
Learning Transferable Visual Models From Natural Language Supervision , Radford, Kim, Hallacy, Ramesh, Goh, Agarwal, Sastry, Askell, Mishkin, Clark, Krueger, Sutskever; 2021 |
Review both summaries |