Seiya Tokui is a researcher at Preferred Networks and also a Ph.D student at the University of Tokyo. He received the master’s degree in mathematical informatics at the University of Tokyo in 2012. He is the lead developer of a deep learning framework, Chainer. His current research/development interests include deep generative learning and the software design and programming models for deep learning.
Computer Science, U. Tokyo (Apr. 2016 – current)
- Supervisor: Issei Sato
Master: Mathematical Informatics, U. Tokyo (Apr. 2010 – Mar. 2012)
- Research theme: machine learning, nearest neighbor search, natural language processing
- Master’s thesis: Learning Hash with Sequential Buckets Partitioning
- Supervisor: Hiroshi Nakagawa
Bachelor: Mathematics, U. Tokyo (Apr. 2006 – Mar. 2010)
- Studied topology and combinatorial optimization
Researcher at Preferred Networks (Oct. 2014 – current)
- Working on machine learning and computer vision for IoT
- Leading the development of Chainer, a framework for deep learning
Researcher/Engineer at Preferred Infrastructure (Apr. 2012 – Oct. 2014)
- Worked on machine learning, natural language processing, and computer vision
- Was mainly engaged in the Jubatus project
- pixiv (Mar. 2011), worked on improvements of recommender systems
- Google Japan (Aug. 2010 – Sep. 2010), worked at Google Japanese Input team (a.k.a. mozc) and created the calculator feature
Publications and Presentations
Conference Papers (refereed)
Seiya Tokui, Issei Sato. Evaluating the Variance of Likelihood-Ratio Gradient Estimators. International Conference on Machine Learning (ICML), 2017.
Weihua Hu, Takeru Miyato, Seiya Tokui, Eiichi Matsumoto, Masashi Sugiyama. Learning Discrete Representations via Information Maximizing Self-Augmented Training. International Conference on Machine Learning (ICML), 2017. [arXiv]
Seiya Tokui, Issei Sato, Hiroshi Nakagawa. Locally Optimized Hashing for Nearest Neighbor Search. In Advances in Knowledge Discovery and Data Mining, 19th Pacic-Asia Conference, PAKDD 2015, Ho Chi Minh City, Vietnam, May 19-22, 2015, Proceedings, Part II, 498–509.
Workshop Papers (refereed)
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.
Shohei Hido, Satoshi Oda and Seiya Tokui. Jubatus: An Open Source Platform for Distributed Online Machine Learning. In Big Learning Workshop at Neural Information Processing Systems (NIPS), 2013.
Seiya Tokui, Kenta Oono, Atsunori Kanemura. Deep Learning Implementations and Frameworks, at the Thirty-first Conference on Artificial Intelligence (AAAI), 2017.
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.
- I have written a Japanese book on online machine learning with three of my colleagues.
- See Japanese version for the domestic conferences and workshops.
Seiya Tokui. Software Japan Award 2017 (for the development of a deep learning framework). Information Processing Society of Japan, 2017.
Chainer: a Framework for Deep Learning (Apr. 2015 – current)
maf: a Build Tool for Parameterized Experiments (Dec. 2012 – Mar. 2015)
- Co-authored with Hiroshi Noji
- GitHub repository
Jubatus: a Distributed Machine Learning Framework (Apr. 2012 – Apr. 2014)
- Developed distributed algorithms for nearest neighbor search and outlier detection
- Official site, GitHub repository
- Programming: C++/Python (advanced), CUDA/C
- Communication: Japanese (native), English