文部科学省 科学技術人材育成費補助事業「テニュアトラック普及・定着」事業

Fontsize

国立大学法人 豊橋技術科学大学 テニュアトラックプログラム

テニュアトラック教員紹介 / Tenure Track Faculty Members

HOME > テニュアトラック教員紹介 > Kazuho WATANABE, Ph.D., Tenure Track Lecturer

Kazuho WATANABE, Ph.D., Tenure Track Lecturer

Research Area

Statistical Learning Theory / Machine Learning

Key Words

Bayesian inference, learning algorithm, data visualization, rate-distortion function, Shannon lower bound

Outreach

Paper(s)

International Conference

  • Shinichi Nakajima, Issei Sato, Masashi Sugiyama, Kazuho Watanabe, and Hiroko Kobayashi,
    "Analysis of variational Bayesian latent Dirichlet allocation: weaker sparsity than MAP,"
    Advances in Neural Information Processing Systems (NIPS2014), to appear, December 8-13, Montreal, Canada, 2014.
  • Koto Nohno, Hsiang-Yun Wu, Kazuho Watanabe, Shigeo Takahashi, and Issei Fujishiro,
    "Spectral-based contractible parallel coordinates,"
    Proceedings of the 18th International Conference on Information Visualisation (iV2014), Paris, France, July 15-18, pp.7-12, 2014.
  • Andrew Barron, Teemu Roos, and Kazuho Watanabe,
    "Bayesian Properties of Normalized Maximum Likelihood and its Fast Computation,"
    Proceedings of the IEEE International Symposium on Information Theory (ISIT), Honolulu, Hawaii, USA, June 29-July 7, pp.1667-1671, 2014.

Invited Lecture

  • Kazuho Watanabe,
    "Rate-Distortion Analysis for an Epsilon-Insensitive Loss Function,"
    Proceedings of 2014 Workshop on Information Theoretic Methods in Science and Engineering, Honolulu, Hawaii, USA, 2014, to appear.

Awards

  • SITA encouragement award (Subsociety of Information Theory and its Applications), 2013
  • Best paper method award of the GfKl (German Classification Society), 2010.
  • Best paper award of the JNNS (Japanese Neural Network Society), 2008.









ページトップ