Deep Learning
Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics
Niru Maheswaranathan, Alex Williams, Matthew Golub, Surya Ganguli, David Sussillo
Recurrent neural networks (RNNs) are a popular tool for sequence modelling tasks.
Reflection Separation using a Pair of Unpolarized and Polarized Images
Youwei Lyu, Zhaopeng Cui, Si Li, Marc Pollefeys, Boxin Shi
Neural Information Processing Systems http://nips.cc/
AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification
Ronghui You, Zihan Zhang, Ziye Wang, Suyang Dai, Hiroshi Mamitsuka, Shanfeng Zhu
Traditionally most methods used bag-of-words (BOW) as inputs, ignoring word context as well as deep semantic information.
Efficient Meta Learning via Minibatch Proximal Update
Pan Zhou, Xiaotong Yuan, Huan Xu, Shuicheng Yan, Jiashi Feng
Hessian matrix but as a result the convergence and generalization guarantees remain largely mysterious for MAML.
A Closer Look at Accuracy vs. Robustness Y ao-Y uan Y ang 1 Cyrus Rashtchian
We explore combining dropout with robust training methods and obtain better generalization.