Technology
Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
Kevin Liang, Guoyin Wang, Yitong Li, Ricardo Henao, Lawrence Carin
Neural Information Processing Systems http://nips.cc/
7e9e346dc5fd268b49bf418523af8679-AuthorFeedback.pdf
Commentsonpresentation: Thank you forthehelpful suggestions. We focus on Mercer kernel with formkฮธ(zt, z) = qฮธ(z|t z) = h|t h. Even so, we obtain SOTA results for recurrent models on all document classification tasks, with the19 exceptionofAGNews,forwhichwe'recompetitive.
Learning to Exploit Stability for 3D Scene Parsing
Yilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, Bill Freeman, Josh Tenenbaum, Jiajun Wu
Physics is a rich and universal cue that we exploit to enhance scene understanding.
ed91353f700d113e5d848c7e04a858b0-Paper-Conference.pdf
Definition 1.Let p (r) := P s,ap (r|s, a), p (rc|s, a) := P
ed7b8e1312f6ba8af6e4316dcd28bb3d-Paper-Conference.pdf
Wefindalarge range of behavior that can be precisely characterized by a new measure ofconfounding strength.
Multi-Task Learning as Multi-Objective Optimization
Neural Information Processing Systems http://nips.cc/
Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse
James Lucas, George Tucker, Roger B. Grosse, Mohammad Norouzi
Neural Information Processing Systems http://nips.cc/
