Industry
Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
DRAE and then generalize it to the CF setting. The synergy between denoising and CF enables CRAE to make accurate recommendations while learning to fill in the blanks in sequences.
Inverse Filtering for Hidden Markov Models
Robert Mattila, Cristian Rojas, Vikram Krishnamurthy, Bo Wahlberg
This paper considers a number of related inverse filtering problems for hidden Markov models (HMMs).
A Locally Adaptive Normal Distribution
Georgios Arvanitidis, Lars K. Hansen, Sรธren Hauberg
We further extend the LAND to mixture models, and provide the corresponding EM algorithm.
Real Time Image Saliency for Black Box Classifiers
Neural Information Processing Systems http://nips.cc/
Learning A Structured Optimal Bipartite Graph for Co-Clustering
Feiping Nie, Xiaoqian Wang, Cheng Deng, Heng Huang
Clustering has long been a fundamental topic in unsupervised learning.
Flexible neural representation for physics prediction
Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li F. Fei-Fei, Josh Tenenbaum, Daniel L. Yamins
Neural Information Processing Systems http://nips.cc/
A Mathematical Model For Optimal Decisions In A Representative Democracy
Malik Magdon-Ismail, Lirong Xia
This happens in noisy settings when voters have limited information.
Fast deep reinforcement learning using online adjustments from the past
Steven Hansen, Alexander Pritzel, Pablo Sprechmann, Andre Barreto, Charles Blundell
We propose Ephemeral V alue Adjusments (EV A): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer.
Improved Network Robustness with Adversary Critic
Alexander Matyasko, Lap-Pui Chau
Ideally, what confuses neural network should be confusing to humans.
Adversarially Robust Generalization Requires More Data
Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high confidence.