Takeru Miyato

Affiliation

I am now working at Preferred Networks, Inc. as a part-time researcher.
I was a Master student in Integrated System Biology Labratory,
Department of System Science, Graduate school of Informatics, Kyoto University.

Research Interests

• Learning the structure of neural networks.
• Integrated training of generative models and discriminative models.
• Semi-supervised and unsupervised learning of disentanglement.

Education

• M.S. Informatics – Graduate School of Informatics, Kyoto University, April 2014 - March 2016.
• B.E. Electronic Engineering – Kyoto University, April 2010 - March 2014.

Publications

1. Masanori Koyama, Kentaro Minami, Takeru Miyato, and Yarin Gal
   Contrastive Representation Learning with Trainable Augmentation Channel.
   {Bayesian Deep Learning/Self-Supervised Learning - Theory and Practice} Workshop at NeurIPS. 2021.
   [arXiv]
2. Takeru Miyato, Masanori Koyama
   Generative Adversarial Networks.
   A book chapter in Computer Vision: A Reference Guide. Ed. by Katsushi Ikeuchi. Springer. 2021
   [paper link]
3. Amir Najafi, Shin-ichi Maeda, Masanori Koyama, and Takeru Miyato
   Robustness to adversarial perturbations in learning from incomplete data.
   Advances in Neural Information Processing Systems (NeurIPS). 2019
   
[code] [paper link]
4. 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]
5. Ken Nakanishi, Shin-ichi Maeda, Takeru Miyato and Daisuke Okanohara
   Neural Multi-scale Image Compression.
   ACCV, 2018. (accepted for oral presentation)
   [arXiv]
6. 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]
7. Takeru Miyato and Masanori Koyama
   cGANs with Projection Discriminator.
   ICLR, 2018.
   [code] [OpenReview]
8. 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]
9. 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]
10. Takeru Miyato, Daisuke Okanohara, Shin-ichi Maeda and Masanori Koyama
    Synthetic gradient methods with Virtual Forward-Backward Networks.
    Workshop at ICLR, 2017.
    [poster] [OpenReview]
11. 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

• Especially skilled in Pytorch, TensorFlow, Chainer and Theano, python based deep learning frameworks.

Hosted on GitHub Pages — Theme by orderedlist