Deep Learning
Natural Value Approximators: Learning when to Trust Past Estimates
Zhongwen Xu, Joseph Modayil, Hado P. van Hasselt, Andre Barreto, David Silver, Tom Schaul
Furthermore, as the interpolation is learned and state-dependent, our method can deal with heterogeneous observability.
Cold-Start Reinforcement Learning with Softmax Policy Gradient
The exposure-bias problem has recently received attention in neural-network settings with the "data as demonstrator" [
Filtering Variational Objectives
Chris J. Maddison, John Lawson, George Tucker, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet, Yee Teh
Neural Information Processing Systems http://nips.cc/
Language Modeling with Recurrent Highway Hypernetworks
Neural Information Processing Systems http://nips.cc/
The Reversible Residual Network: Backpropagation Without Storing Activations
Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse
Therefore, the activations for most layers need not be stored in memory during backpropagation.
Dual Path Networks
Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, Jiashi Feng
Network (DPN) for image classification which presents a new topology of connection paths internally.
Overcoming Catastrophic Forgetting by Incremental Moment Matching
Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun, Jung-Woo Ha, Byoung-Tak Zhang
Neural Information Processing Systems http://nips.cc/
Multimodal Learning and Reasoning for Visual Question Answering
Typically, a VQA model is comprised of two modules for learning the question and the image representations, and a third module for fusing the representations into a single multimodal representation.
Unbounded cache model for online language modeling with open vocabulary
Edouard Grave, Moustapha M. Cisse, Armand Joulin
Neural Information Processing Systems http://nips.cc/
Preventing Gradient Explosions in Gated Recurrent Units
Sekitoshi Kanai, Yasuhiro Fujiwara, Sotetsu Iwamura
Neural Information Processing Systems http://nips.cc/