Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Hiroki NAGANUMA"'
Publikováno v:
Nihon Kikai Gakkai ronbunshu, Vol 85, Iss 879, Pp 18-00500-18-00500 (2019)
Selected from various Eigen modes of blading, nodal diameter κ= 0 and κ= 1 are both related to shaft torsional and/or axial vibration and shaft bending vibrations respectively. In order to avoid the possibility of 2f (f=power system frequency) from
Externí odkaz:
https://doaj.org/article/0cc852d82aab4b0aaccbac70b58f2023
Autor:
Rio Yokota, Hiroki Naganuma
Publikováno v:
CCGRID
Classical learning theory states that when the number of parameters of the model is too large compared to the data, the model will overfit and the generalization performance deteriorates. However, it has been empirically shown that deep neural networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52114794af12c0568f3e2f2a7fc6aa2a
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100793661
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100793661
Publikováno v:
HPCS
The open source frameworks of deep learning including TensorFlow, Caffe, Torch, etc. are widely used all over the world and its acceleration have great meaning. In these frameworks, a lot of computation time is spent on convolution, and highly tuned
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75891ab662b5fbe661c38bf153dcfa8c
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100751142
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100751142
Publikováno v:
The Proceedings of the Dynamics & Design Conference. 2018:427
Publikováno v:
The Proceedings of Mechanical Engineering Congress, Japan. 2017:W111002
Publikováno v:
The Proceedings of The Computational Mechanics Conference. :004
Publikováno v:
The Proceedings of the Bioengineering Conference Annual Meeting of BED/JSME. :245-246