yoshua bengio
Towards Deep Conversational Recommendations
Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, Chris Pal
Foreachparticipantit threelabels: the "suggested" label (binary), the "seen" label (categoricalwiththree "liked" label (categoricalwiththreeclasses) foratotalof 14 dimensions.
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Xiaohan Ding, guiguang ding, Xiangxin Zhou, Yuchen Guo, Jungong Han, Ji Liu
DNN pruning is an approach for deep model compression, which aimsateliminating someparameters withtolerable performance degradation.
Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
Chao Yang, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu, Junzhou Huang, Chuang Gan
Incontrast toLearning fromDemonstration (LfD) that involves both action and state supervision, LfO is more practical in leveraging previously inapplicable resources (e.g.
Adaptive Cross-Modal Few-shot Learning
Chen Xing, Negar Rostamzadeh, Boris Oreshkin, Pedro O. O. Pinheiro
Neural Information Processing Systems http://nips.cc/
Multi-Task Zipping via Layer-wise Neuron Sharing
Xiaoxi He, Zimu Zhou, Lothar Thiele
Neural Information Processing Systems http://nips.cc/
Visualizing the Loss Landscape of Neural Nets
Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein
Forsurfaceplotsof ResNet-56, see Figure 1.
Visualizing the PHATE of Neural Networks
Scott Gigante, Adam S. Charles, Smita Krishnaswamy, Gal Mishne
Wedemonstrate that our visualization provides intuitive, detailed summaries of the learning dynamics beyond simple global measures (i.e., validation loss and accuracy), without the need to access validation data. Furthermore, M-PHATE better captures both the dynamics and community structure of the hidden units as compared to visualization based on standard dimensionality reduction methods (e.g., ISOMAP,t-SNE).
Adversarial Multiple Source Domain Adaptation
Han Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, Joao P. Costeira, Geoffrey J. Gordon
We baselines: FCN52], abasicnetw17], implemented 7 yondigitclassification.
Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
Aaron Voelker, Ivana Kajić, Chris Eliasmith
LSTMs are designed to help alleviate the issue of vanishing and exploding gradients commonly associatedwithtrainingRNNs[5].
