User profiles for M. Sugiyama

Masashi Sugiyama

- Verified email at ku-tokyo.ac.jp - Cited by 36109

Masaya Sugiyama

- Verified email at hosp.ncgm.go.jp - Cited by 9539

Munetaka Sugiyama

- Verified email at bs.su-tokyo.ac.jp - Cited by 4278

[HTML][HTML] Deep learning, reinforcement learning, and world models

…, Y LeCun, M Sahani, D Precup, D Silver, M Sugiyama… - Neural Networks, 2022 - Elsevier
Deep learning (DL) and reinforcement learning (RL) methods seem to be a part of indispensable
factors to achieve human-level or super-human AI systems. On the other hand, both DL …

Human dental pulp stem cells with highly angiogenic and neurogenic potential for possible use in pulp regeneration

M Nakashima, K Iohara, M Sugiyama - Cytokine & growth factor reviews, 2009 - Elsevier
Dental caries is a common public health problem, causing early loss of dental pulp and
resultant tooth loss. Dental pulp has important functions to sustain teeth providing nutrient and …

Organogenesis in vitro

M Sugiyama - Current opinion in plant biology, 1999 - Elsevier
… Author links open overlay panel Munetaka Sugiyama … I Yasutani, S Ozawa, T Nishida,
M Sugiyama, A Komamine … S Ozawa, I Yasutani, H Fukuda, A Komamine, M Sugiyama

Role of adaptor TRIF in the MyD88-independent toll-like receptor signaling pathway

…, H Sanjo, O Takeuchi, M Sugiyama, M Okabe… - Science, 2003 - science.org
Stimulation of Toll-like receptors (TLRs) triggers activation of a common MyD88-dependent
signaling pathway as well as a MyD88-independent pathway that is unique to TLR3 and …

Genome-wide association of IL28B with response to pegylated interferon-α and ribavirin therapy for chronic hepatitis C

Y Tanaka, N Nishida, M Sugiyama, M Kurosaki… - Nature …, 2009 - nature.com
The recommended treatment for patients with chronic hepatitis C, pegylated interferon-α (PEG-IFN-α)
plus ribavirin (RBV), does not provide sustained virologic response (SVR) in all …

Co-teaching: Robust training of deep neural networks with extremely noisy labels

…, M Xu, W Hu, I Tsang, M Sugiyama - Advances in neural …, 2018 - proceedings.neurips.cc
Deep learning with noisy labels is practically challenging, as the capacity of deep models is
so high that they can totally memorize these noisy labels sooner or later during training. …

[BOOK][B] Dataset shift in machine learning

J Quiñonero-Candela, M Sugiyama, A Schwaighofer… - 2022 - books.google.com
… In chapter 7 Masashi Sugiyama and coworkers also discuss the problems of model selection
… N(x; m, K) will be used to denote the Gaussian distribution function of x, with mean m and …

[PDF][PDF] Covariate shift adaptation by importance weighted cross validation.

M Sugiyama, M Krauledat, KR Müller - Journal of Machine Learning …, 2007 - jmlr.org
… regression called subspace information criterion (SIC) (Sugiyama and Ogawa, 2001) was
similarly extended to be still unbiased (Sugiyama and Müller, 2005). Although these model …

Direct importance estimation with model selection and its application to covariate shift adaptation

M Sugiyama, S Nakajima, H Kashima… - Advances in neural …, 2007 - proceedings.neurips.cc
When training and test samples follow different input distributions (ie, the situation called\emph
{covariate shift}), the maximum likelihood estimator is known to lose its consistency. For …

[PDF][PDF] Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis.

M Sugiyama - Journal of machine learning research, 2007 - jmlr.org
… analysis is available from the author’s website: ‘http://sugiyama-www.cs.titech.ac.jp/sugi/software/…
A MATLAB implementation is available from ‘http://sugiyama-www.cs.titech.ac.jp/sugi/…