Affiliation
I am curretnly a Ph.D. student at Autonomous Vision Group, University of Tübingen under ELLIS Ph.D program. I am supervised by Andreas Geiger (UTübingen) and Max Welling (UvA).
I am also working for Preferred Networks, Inc. as a part-time researcher.
I worked at ATR, Google Brain (as an intern). I did my Master at Integrated System Biology Labratory, Kyoto University.
Research Interests
I am engaged in machine learning research.
I have strong interest in scalable and simple machine learning algorithm.
My current focuses are
- Learning symmetry structure from observations
Education
- Ph.D. Computer Science – University of Tübingen, Sep. 2022 - (now)
- M.S. Informatics – Graduate School of Informatics, Kyoto University, April 2014 - March 2016.
- B.E. Electronic Engineering – Kyoto University, April 2010 - March 2014.
Selected Publications
For the full publication list, please see my Google Scholar profile
-
Takeru Miyato*, Masanori Koyama*, and Kenji Fukumizu
Unsupervised Learning of Equivariant Structure from Sequences.
NeurIPS. 2022.
[code] [arXiv] [OpenReview] [poster]
-
Takeru Miyato, Masanori Koyama
Generative Adversarial Networks.
A book chapter in Computer Vision: A Reference Guide. Ed. by Katsushi Ikeuchi. Springer. 2021
[paper link]
-
Amir Najafi, Shin-ichi Maeda, Masanori Koyama, and Takeru Miyato
Robustness to adversarial
perturbations in learning from incomplete data.
NeurIPS. 2019
[code] [paper link]
-
Takeru Miyato, Shin-ichi Maeda, Masanori Koyama and Shin Ishii
Virtual Adversarial Training : A Regularization Method for Supervised and Semi-Supervised Learning.
IEEE TPAMI, 2019.
(extended version of the paper published at ICLR2016)
[code (TF)] [code (Chainer)] [arXiv]
-
Takeru Miyato, Toshiki Kataoka, Masanori Koyama and Yuichi Yoshida
Spectral Normalization for Generative Adversarial Networks.
ICLR, 2018. (accepted for oral presentation)
[code]
[code (on ImageNet)]
[OpenReview]
-
Takeru Miyato and Masanori Koyama
cGANs with Projection Discriminator.
ICLR, 2018.
[code]
[OpenReview]
-
Weihua Hu, Takeru Miyato, Seiya Tokui, Eiichi Matsumoto and Masashi Sugiyama
Learning Discrete Representations via Information Maximizing Self Augmented Training.
ICML, 2017.
[code (by @weihua916)]
[arXiv]
-
Takeru Miyato, Andrew M. Dai and Ian Goodfellow
Adversarial Training Methods for Semi-Supervised Text Classification.
ICLR, 2017.
[code (Chainer, by @aonotas)]
[code (TF)]
[arXiv]
[slide]
[poster]
[OpenReview]
-
Takeru Miyato, Shin-ichi Maeda, Masanori Koyama, Ken Nakae and Shin Ishii
Distributional Smoothing with Virtual Adversarial Training.
ICLR, 2016.
[code]
[arXiv]
[slide]
[poster]
Working Experiences
- Preferred Networks Inc., Tokyo, Japan, 09/2016 - (now)
-
Part-time researcher. 11/2021 -
-
Full-time researcher. 06/2016 - 09/2021
- Advanced Telecommunications Research Institute International (ATR), Kyoto, Japan, 06/2016 - 08/2016
-
Full-time research engineer, 06/2016 - 08/2016
- Google Inc., Mountain View CA, 01/2016 - 05/2016.
-
Software Engineer Intern (Research oriented) at Google Brain, under supervision of Dr. Andrew M. Dai and Dr. Ian Goodfellow.
Skills
Python, MATLAB, Objective-C, C#, C, C++, OpenGL.
- Especially skilled in Pytorch, TensorFlow, Chainer and Theano, python based deep learning frameworks.
Hosted on GitHub Pages — Theme by orderedlist