Zobrazeno 1 - 10 of 38 pro vyhledávání: '"Wataru Kumagai"'
1
Akademický článek
Spectral Embedded Deep Clustering
Autor: Yuichiro Wada, Shugo Miyamoto, Takumi Nakagama, Léo Andéol, Wataru Kumagai, Takafumi Kanamori
Publikováno v: Entropy, Vol 21, Iss 8, p 795 (2019)
We propose a new clustering method based on a deep neural network. Given an unlabeled dataset and the number of clusters, our method directly groups the dataset into the given number of clusters in the original space. We use a conditional discrete pr
Externí odkaz: https://doaj.org/article/df8e76ccc40345bba778cdd58568d1a5
Zobrazit plný text záznamu
2
Akademický článek
Miniaturization and improvement of cogging torque characteristic for IPM type 5-DOF self-bearing motor
Autor: Kenichi MATSUDA, Wataru KUMAGAI, Ryou KONDO, Toru MASUZAWA
Publikováno v: Nihon Kikai Gakkai ronbunshu, Vol 81, Iss 827, Pp 14-00567-14-00567 (2015)
5-DOF self-bearing motor possesses the functions of a motor, two radial active magnetic bearings (AMBs), and an axial AMB. It is possible to downsize the AMB system while still maintaining a high level of support performance. In a 5-DOF self-bearing
Externí odkaz: https://doaj.org/article/f90df08c54104b2cbbc65d41e561c375
Zobrazit plný text záznamu
6
Uncertainty propagation for dropout-based Bayesian neural networks
Autor: Wataru Kumagai, Takafumi Kanamori, Yuki Mae
Publikováno v: Neural Networks. 144:394-406
Uncertainty evaluation is a core technique when deep neural networks (DNNs) are used in real-world problems. In practical applications, we often encounter unexpected samples that have not seen in the training process. Not only achieving the high-pred
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0780b8b5b098b66694bea702e7c9b73c
https://doi.org/10.1016/j.neunet.2021.09.005
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje