Preferred research Blog (Japanese)

Preferred research Blog (English)



Slide Share




– Deep Learning Summit, San Francisco 2017; Deep Learning: IoT’s Driving Engine

– Amazon Picking Challenge 2016 PFN pick task

– Drone control based on Deep Reinforcement Learning in CEATEC JAPAN 2016
Introduction(Japanese) / Side view / Bird view

– Smart picking robot based on Deep learning in CEATEC 2016

– Experimental result of CityScape datasets (segmentation) 2016 version



– 2017 Japan-U.S. Innovation Awards「Emerging Leader Award」(2017年7月)

– FT ArcelorMittal Boldness in Business Awards (2017年3月)

– 第3回日本ベンチャー大賞「経済産業大臣賞」(2017年2月)

– 第1回JEITAベンチャー賞(2016年3月)

– Forbes JAPAN’s CEO OF THE YEAR 2016「最もイノベーティブなスタートアップ1位」(2016年9月)

– IT Pro EXPO Award 2014優秀賞「ディープラーニングを応用した映像解析ソリューション」(2014年10月)



– 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


Shin-ichi Maeda, Yasuhiro Fujita and others, 共立出版「速習強化学習-基礎理論とアルゴリズム-」(Algorithms for Reinforcement Learningの翻訳本)