Presentation 2018-05-19
On Simple Growing Reservoir Computing Systems
Naoki Sakamoto, Toshimichi Saito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies basic function of a simple reservoir computing system. The system is based on a ring-type recurrent network with growing structure. The number of neurons can increase flexibly depending on problems. Training of weighting parameters is performed by a simple version of the differential evolution. Using elementary time-series approximation problems, the network function is investigated.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reservoir Computing / Differential Evolution / Time-series prediction
Paper # NC2018-4
Date of Issue 2018-05-12 (NC)

Conference Information
Committee MBE / NC
Conference Date 2018/5/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Univ. of Toyama
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kazuki Nakajima(Univ. of Toyama) / Masafumi Hagiwara(Keio Univ.)
Vice Chair Masaki Kyoso(TCU) / Yutaka Hirata(Chubu Univ.)
Secretary Masaki Kyoso(Toyama Pref. Univ.) / Yutaka Hirata(Kindai Univ.)
Assistant Kim Juhyon(Univ. of Toyama) / Takumi Kobayashi(YNU) / Yoshihisa Shinozawa(Keio Univ.) / Keiichiro Inagaki(Chubu Univ.)

Paper Information
Registration To Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On Simple Growing Reservoir Computing Systems
Sub Title (in English)
Keyword(1) Reservoir Computing
Keyword(2) Differential Evolution
Keyword(3) Time-series prediction
1st Author's Name Naoki Sakamoto
1st Author's Affiliation Hosei University(HU)
2nd Author's Name Toshimichi Saito
2nd Author's Affiliation Hosei University(HU)
Date 2018-05-19
Paper # NC2018-4
Volume (vol) vol.118
Number (no) NC-45
Page pp.pp.15-18(NC),
#Pages 4
Date of Issue 2018-05-12 (NC)