Blogs


Preferred research Blog (Japanese)


Preferred research Blog (English)

 

Slides


Slide Share

 

Videos

 

– Deep Learning Summit, San Francisco 2017; Deep Learning: IoT’s Driving Engine
http://videos.re-work.co/videos/289-deep-learning-iot-s-driving-engine

– Amazon Picking Challenge 2016 PFN pick task
https://www.youtube.com/embed/w7NgejZMSsA

– Drone control based on Deep Reinforcement Learning in CEATEC JAPAN 2016
Introduction(Japanese) / Side view / Bird view
https://www.youtube.com/embed/2nO3hLPPEX4
https://www.youtube.com/embed/yFCCanSxOE4
https://www.youtube.com/embed/y-HkD3Z5cl8

– Smart picking robot based on Deep learning in CEATEC 2016
https://www.youtube.com/embed/MpWvJhznpQQ

– Experimental result of CityScape datasets (segmentation) 2016 version
https://www.youtube.com/embed/1HJSMR6LW2g

 

Awards

– 2017 Japan-U.S. Innovation Awards「Emerging Leader Award」(2017.Jul.)
http://www.usjinnovate.org/

– FT ArcelorMittal Boldness in Business Awards (2017.Mar.)
https://www.ft.com/content/d5608670-ed57-11e6-930f-061b01e23655
https://live.ft.com/Events/2017/FT-ArcelorMittal-Boldness-in-Business-Awards?=&v=5366219067001

– Third Nippon Venture Awards : METI Minister’s Awards (2017.Feb.)
http://www.meti.go.jp/press/2016/02/20170220006/20170220006.html

– 1st JEITA Venture Award (2016.Mar.)
http://www.jeita.or.jp/cps/activity/venture/

– Forbes JAPAN’s CEO OF THE YEAR 2016 (2016.Sep.)
http://forbesjapan.com/articles/detail/13729

– IT Pro EXPO Award 2014 : Award of Excellence (2014.Oct.)
http://itpro.nikkeibp.co.jp/atcl/news/14/101601417/
http://itpro.nikkeibp.co.jp/atcl/column/14/103000088/111100011

 

Publications


– Seiya Tokui, Kenta Oono, Shohei Hido, Justin Clayton. Chainer: a Next-Generation Open Source Framework for Deep Learning. In Workshop on Machine Learning Systems at Neural Information Processing Systems (NIPS), 2015.


– Oono, K., & Yoshida, Y. (2016). Testing properties of functions on finite groups. Random Structures & Algorithms, 49(3), 579-598.


– (tutorial) Seiya Tokui, Kenta Oono, Atsunori Kanemura, and Toshihiro Kamishima. Deep Learning Implementations and Frameworks, at the 20th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2016.


– (tutorial) Seiya Tokui, Kenta Oono, and Atsunori Kanemura. Deep Learning Implementations and Frameworks, at The Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), 2017.


– Weihua Hu, Takeru Miyato, Seiya Tokui, Eiichi Matsumoto and Masashi Sugiyama. Learning Discrete Representations via Information Maximizing Self Augmented Training. arXiv:1702.08720, 2017.


– Takeru Miyato, Andrew M. Dai and Ian Goodfellow. Adversarial Training Methods for Semi-Supervised Text Classification. International Conference on Learning Representations (ICLR), 2017. (also accepted at Adversarial Training Workshop on NIPS2016, as a spotlight presentation)


– Takeru Miyato, Daisuke Okanohara, Shin-ichi Maeda and Masanori Koyama. Synthetic Gradient Methods with Virtual Forward-Backward Networks. Workshop on International Conference on Learning Representations (ICLR), 2017.

 

Masaki Saito, Eiichi Matsumoto, Shunta Saito. Temporal Generative Adversarial Nets with Singular Value Clipping, ICCV 2017

 

–  Hitoshi Kusano, Ayaka Kume, Eiichi Matsumoto, Jethro Tan. FCN-Based 6D Robotic Grasping for Arbitrary Placed Objects, ICRA 2017

 

–  E. Matsumoto, M. Saito, A. Kume, J. Tan. End-to-End Learning of Object Grasp Poses in the Amazon Robotics Challenge. In Warehouse Picking Automation Workshop, ICRA 2017

 

– Takeru Miyato, Toshiki Kataoka, Masanori Koyama, Yuichi Yoshida. Spectral Normalization for Generative Adversarial Networks, ICML workshop

 

– Sotetsu Koyamada, Yuta Kikuchi, Atsunori Kanemura, Shin-ichi Maeda, Shin Ishii. Neural Sequence Model Training via α-divergence Minimization, ICML 2017 Workshop on Learning to Generate Natural Language

 

– S. Tokui (This work is solely done as a Ph.D. student at Univ. of Tokyo) and I. Sato (Univ. of Tokyo). Evaluating the Variance of Likelihood-Ratio Gradient Estimators, ICML 2017