Wed Sep 01 |
Rectifier Nonlinearities Improve Neural Network Acoustic Models , Maas, Hannun, Ng; 2013 |
Draft Summary |
Sun Sep 05 |
Rectifier Nonlinearities Improve Neural Network Acoustic Models , Maas, Hannun, Ng; 2013 |
Final Summary |
Wed Sep 08 |
On the importance of initialization and momentum in deep learning , Sutskever, Martens, Dahl, Hinton; 2013 |
Draft Summary |
Sun Sep 12 |
On the importance of initialization and momentum in deep learning , Sutskever, Martens, Dahl, Hinton; 2013 |
Final Summary |
Sun Sep 19 |
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , Ioffe, Szegedy; 2015 |
Coding |
Fri Sep 24 |
Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth , Dong, Cordonnier, Loukas; 2021 |
Review both summaries |
Wed Sep 29 |
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention , Katharopoulos, Vyas, Pappas, Fleuret; 2020 |
Draft Summary |
Sun Oct 03 |
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention , Katharopoulos, Vyas, Pappas, Fleuret; 2020 |
Final Summary |
Wed Oct 06 |
Training data-efficient image transformers & distillation through attention , Touvron, Cord, Douze, Massa, Sablayrolles, Jégou; 2020 |
Draft Summary |
Sun Oct 10 |
Training data-efficient image transformers & distillation through attention , Touvron, Cord, Douze, Massa, Sablayrolles, Jégou; 2020 |
Final Summary |
Sun Oct 17 |
Occupancy Networks: Learning 3D Reconstruction in Function Space , Mescheder, Oechsle, Niemeyer, Nowozin, Geiger; 2018 |
Coding |
Fri Oct 22 |
Deformable Convolutional Networks , Dai, Qi, Xiong, Li, Zhang, Hu, Wei; 2017 |
Review both summaries |
Wed Oct 27 |
Point Transformer , Zhao, Jiang, Jia, Torr, Koltun; 2020 |
Draft Summary |
Sun Oct 31 |
Point Transformer , Zhao, Jiang, Jia, Torr, Koltun; 2020 |
Final Summary |
Sun Nov 07 |
A Simple Framework for Contrastive Learning of Visual Representations , Chen, Kornblith, Norouzi, Hinton; 2020 |
Coding |