Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Sho Sonoda"'
A biological neural network in the cortex forms a neural field. Neurons in the field have their own receptive fields, and connection weights between two neurons are random but highly correlated when they are in close proximity in receptive fields. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b4b99fe235ef8cf44b79cbcb60f9115c
Autor:
Shotaro Akaho, Hideitsu Hino, Yuki Kaneda, Noboru Murata, Masahiro Kawasaki, Keita Nakamura, Sho Sonoda, Eri Miyauchi
Publikováno v:
Neural Networks. 108:68-82
Electroencephalography (EEG) is a non-invasive brain imaging technique that describes neural electrical activation with good temporal resolution. Source localization is required for clinical and functional interpretations of EEG signals, and most com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::461bfe8b99155066d3ed1104ba01632f
https://doi.org/10.1016/j.neunet.2018.08.008
https://doi.org/10.1016/j.neunet.2018.08.008
Publikováno v:
BIBM
A common approach to the electroencephalogram (EEG) source localization problem is to estimate the states of current dipoles. However, the dipole estimation problem is difficult because not only is it an inverse problem but also the number of dipoles
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::471022b269ebcd4d0776134998a119b1
https://doi.org/10.1109/bibm.2018.8621504
https://doi.org/10.1109/bibm.2018.8621504
Autor:
Sho Sonoda1 SHO.SONODA@RIKEN.JP, Noboru Murata2 NOBORU.MURATA@EB.WASEDA.AC.JP
Publikováno v:
Journal of Machine Learning Research. 2019, Vol. 20 Issue 2-29, p1-52. 52p.
Publikováno v:
ISIJ International. 52:1086-1091
A statistical model for predicting the liquid steel temperature in the ladle and in the tundish is developed. Given a large data set in a steelmaking process, the proposed model predicts the temperature in a seconds with a good accuracy. The data are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2169f56422c5815da40f5d584676b37
https://doi.org/10.2355/isijinternational.52.1086
https://doi.org/10.2355/isijinternational.52.1086
Autor:
Sho Sonoda, Noboru Murata
This paper presents an investigation of the approximation property of neural networks with unbounded activation functions, such as the rectified linear unit (ReLU), which is the new de-facto standard of deep learning. The ReLU network can be analyzed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2ecb6ba7ee4830bd75ea302b8cf9daec
Autor:
Noboru Murata, Sho Sonoda
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2014 ISBN: 9783319111780
ICANN
ICANN
A new sampling learning method for neural networks is proposed. Derived from an integral representation of neural networks, an oracle probability distribution of hidden parameters is introduced. In general rigorous sampling from the oracle distributi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65ad88ec4ed45aa6ee4512e2668d33e2
https://doi.org/10.1007/978-3-319-11179-7_68
https://doi.org/10.1007/978-3-319-11179-7_68
Publikováno v:
IFAC Proceedings Volumes. 45:270-271
Controlling temperature of molten steel is crucial for product quality in continuous casting. In this paper, sensitivity analysis is carried out on a statistical model for predicting temperature in tundish, and influential operations for controlling
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c3b8de36fb1baad272fe26a6861de12
https://doi.org/10.3182/20120910-3-jp-4023.00047
https://doi.org/10.3182/20120910-3-jp-4023.00047
Autor:
Hiroyuki Nakamoto, Futoshi Kobayashi, Hayato Kanno, Nobuaki Imamura, Fumio Kojima, Tadashi Maeda, Sho Sonoda
Publikováno v:
The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec). 2012:1A2-H05_1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8253d5a7e097e35b3a538701b5c1b821
https://doi.org/10.1299/jsmermd.2012._1a2-h05_1
https://doi.org/10.1299/jsmermd.2012._1a2-h05_1
Autor:
Futoshi Kobayashi, Kazuhiro Sasabe, Hidenori Shirasawa, Sho Sonoda, Nobuaki Imamura, Fumio Kojima, Tadashi Maeda, Hiroyuki Nakamoto
Publikováno v:
The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec). 2010:2A2-C20_1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::546addea871992ed4e3dc8bff523e747
https://doi.org/10.1299/jsmermd.2010._2a2-c20_1
https://doi.org/10.1299/jsmermd.2010._2a2-c20_1