| Fri Sep 03 |
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks , Saxe, McClelland, Ganguli; 2013 |
Review both summaries |
| Sun Sep 12 |
ADADELTA: An Adaptive Learning Rate Method , Zeiler; 2012 |
Coding |
| Wed Sep 15 |
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization , Qiao, Wang, Liu, Shen, Yuille; 2019 |
Draft Summary |
| Sun Sep 19 |
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization , Qiao, Wang, Liu, Shen, Yuille; 2019 |
Final Summary |
| Wed Sep 22 |
Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth , Dong, Cordonnier, Loukas; 2021 |
Draft Summary |
| Sun Sep 26 |
Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth , Dong, Cordonnier, Loukas; 2021 |
Final Summary |
| Fri Oct 01 |
Reformer: The Efficient Transformer , Kitaev, Kaiser, Levskaya; 2020 |
Review both summaries |
| Sun Oct 10 |
Transformer in Transformer , Han, Xiao, Wu, Guo, Xu, Wang; 2021 |
Coding |
| Wed Oct 13 |
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections , Martin-Brualla, Radwan, Sajjadi, Barron, Dosovitskiy, Duckworth; 2020 |
Draft Summary |
| Sun Oct 17 |
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections , Martin-Brualla, Radwan, Sajjadi, Barron, Dosovitskiy, Duckworth; 2020 |
Final Summary |
| Wed Oct 20 |
Deformable Convolutional Networks , Dai, Qi, Xiong, Li, Zhang, Hu, Wei; 2017 |
Draft Summary |
| Sun Oct 24 |
Deformable Convolutional Networks , Dai, Qi, Xiong, Li, Zhang, Hu, Wei; 2017 |
Final Summary |
| Fri Oct 29 |
PointCNN: Convolution On $\mathcal{X}$-Transformed Points , Li, Bu, Sun, Wu, Di, Chen; 2018 |
Review both summaries |
| Sun Nov 07 |
Large-Scale Long-Tailed Recognition in an Open World , Liu, Miao, Zhan, Wang, Gong, Yu; 2019 |
Coding |