First International Workshop on Symbolic-Neural Learning (SNL-2017)

July 7-8, 2017
Nagoya Congress Center (Nagoya, Japan)

Program

Friday, July 7

13:00-13:10Opening
13:10-14:10 Keynote talk I (invited): Yoshua Bengio (University of Montreal)
14:10-14:30 Coffee break
14:30-15:30 Keynote talk II: Masashi Sugiyama (RIKEN/University of Tokyo)
15:30-15:40 Break
15:40-17:20 Session 1: Computer Vision
Weihua Hu (University of Tokyo/RIKEN), Takeru Miyato (Preferred Networks), Seiya Tokui (Preferred Networks/ University of Tokyo), Eiichi Matsumoto (Preferred Networks/ University of Tokyo) and Masashi Sugiyama (RIKEN/ University of Tokyo)Learning Discrete Representations via Information Maximizing Self-Augmented Training
Ruotian Luo (Toyota Technological Institute at Chicago) and Gregory Shakhnarovich (Toyota Technological Institute at Chicago) Comprehension-Guided Referring Expressions
Tristan Hascoet (Kobe University), Yasuo Ariki (Kobe University) and Tetsuya Takiguchi (Kobe University) Semantic Web and Zero-Shot Learning of Large Scale Visual Classes
Bowen Shi (Toyota Technological Institute at Chicago), Taehwan Kim (California Institute of Technology), Jonathan Keane (University of Chicago), Weiran Wang (Toyota Technological Institute at Chicago), Hao Tang (Toyota Technological Institute at Chicago), Gregory Shakhnarovich (Toyota Technological Institute at Chicago), Diane Brentari (University of Chicago) and Karen Livescu (Toyota Technological Institute at Chicago) Neural Models for Fingerspelling Recognition from Video
18:00-20:00 Banquet

Saturday, July 8

9:00-10:00 Keynote talk III (invited): William Cohen (Carnegie Mellon University)
10:00-10:20 Coffee break
10:20-11:35 Session 2: Speech & Language
Andrea F. Daniele (Toyota Technological Institute at Chicago), Mohit Bansal (University of North Carolina at Chapel Hill) and Matthew Walter (Toyota Technological Institute at Chicago) Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation
Shubham Toshniwal (Toyota Technological Institute at Chicago), Hao Tang (Toyota Technological Institute at Chicago), Liang Lu (Toyota Technological Institute at Chicago) and Karen Livescu (Toyota Technological Institute at Chicago) Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition
John Wieting (Toyota Technological Institute at Chicago), Mohit Bansal(University of North Carolina Chapel Hill), Kevin Gimpel (Toyota Technological Institute at Chicago) and Karen Livescu (Toyota Technological Institute at Chicago) Neural Architectures for Modeling Compositionality in Natural Language
11:35-13:30 Lunch break
13:30-14:30 Keynote talk IV: Jun-ichi Tsujii (National Institute of Advanced Industrial Science and Technology)
14:30-15:30 Poster Session
Matthew J. Holland (Nara Institute of Science and Technology) and Kazushi Ikeda (Nara Institute of Science and Technology) Memory, Bias, and Variance Reduction
Zhenghang Cui (University of Tokyo), Issei Sato (University of Tokyo/RIKEN) and Masashi Sugiyama (University of Tokyo/RIKEN) Stochastic Divergence Minimization for Biterm Topic Model
Yin Jun Phua (Tokyo Institute of Technology), Sophie Tourret (National Institute of Informatics) and Katsumi Inoue (National Institute of Informatics, Tokyo Institute of Technology) Learning Logic Program Representation From Delayed Interpretation Transition Using Recurrent Neural Networks
Haiping Huang (RIKEN), Alireza Goudarzi (RIKEN) and Taro Toyoizumi (RIKEN) Combining DropConnect and Feedback Alignment for Efficient Regularization in Deep Networks
Jen-Tzung Chien (National Chiao Tung University) and Ching-Wei Huang (National Chiao Tung University) Variational and Adversarial Domain Adaptation
Miki Ueno (Toyohashi University of Technology) Comic Book Interpretation based on Deep Neural Networks
Nicholas Altieri (University of California Berkeley), Sherdil Niyaz (University of California Berkeley), Samee Ibraheem (University of California Berkeley) and John Denero (University of California Berkeley) Improved Word and Symbol Embedding for Part-of-Speech Tagging
Marc Evrard (Toyota Technological Institute), Makoto Miwa (Toyota Technological Institute) and Yutaka Sasaki (Toyota Technological Institute)TTI's Approaches to Symbolic-Neural Learning (*)
15:30-17:35 Session 3: New Learning Approaches
Han Bao (University of Tokyo), Masashi Sugiyama (The University of Tokyo/RIKEN), Issei Sato (University of Tokyo/RIKEN) and Tomoya Sakai(University of Tokyo/RIKEN) Risk Minimization Framework for Multiple Instance Learning from Positive and Unlabeled Bags
Tomoya Sakai(University of Tokyo/RIKEN), Marthinus Christoffel Du Plessis (University of Tokyo), Gang Niu (University of Tokyo) and Masashi Sugiyama (University of Tokyo/RIKEN) Semi-Supervised Classification based on Positive-Unlabeled Classification
Tetsuya Hada (Osaka University/RIKEN), Akifumi Okuno (Kyoto University/RIKEN) and Hidetoshi Shimodaira (Kyoto University/RIKEN) Deep Multi-view Representation Learning Based on Adaptive Weighted Similarity
Makoto Yamada (RIKEN/JST/PRESTO), Koh Takeuchi (NTT CS Labs), Tomoharu Iwata (NTT CS Labs), John Shawe-Taylor (University College London) and Samuel Kaski (Aalto University) Localized Lasso for High-Dimensional Regression
Tim Rocktäschel (University of Oxford) and Sebastian Riedel (University College London) Neural Theorem Provers
17:40-17:50Closing
(*) Sponsor exhibition