Presentation 2019-08-02
Effect of shapes of activation functions on predictability in the echo state network
Hanten Chang, Shinji Nakaoka, Hiroyasu Ando,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We investigate prediction accuracy for time series of Echo state networks with respect to several kinds of activation functions. As a result, we found that some kinds of activation functions with an appropriate nonlinearity show high performance compared to the conventional sigmoid function.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Echo State Network / activation function / attractor reconstruction
Paper # CCS2019-23
Date of Issue 2019-07-25 (CCS)

Conference Information
Committee CCS / IN
Conference Date 2019/8/1(2days)
Place (in Japanese) (See Japanese page)
Place (in English) KIKI SHIRETOKO NATURAL RESORT
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Makoto Naruse(NICT) / Takuji Kishida(NTT-AT)
Vice Chair Shigeki Shiokawa(Kanagawa Inst. of Tech.) / Tetsuya Asai(Hokkaido Univ.) / Kenji Ishida(Hiroshima City Univ.)
Secretary Shigeki Shiokawa(Hiroshima City Univ.) / Tetsuya Asai(Kanagawa Inst. of Tech.) / Kenji Ishida(NTT Communications)
Assistant Hidehiro Nakano(Tokyo City Univ.) / Kazuki Nakada(Tsukuba Univ. of Tech.) / Hiroyasu Ando(Tsukuba Univ.) / Takashi Matsubara(Kobe Univ.)

Paper Information
Registration To Technical Committee on Complex Communication Sciences / Technical Committee on Information Networks
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Effect of shapes of activation functions on predictability in the echo state network
Sub Title (in English)
Keyword(1) Echo State Network
Keyword(2) activation function
Keyword(3) attractor reconstruction
1st Author's Name Hanten Chang
1st Author's Affiliation University of Tsukuba(Univ. of Tsukuba)
2nd Author's Name Shinji Nakaoka
2nd Author's Affiliation Hokkaido University(Hokkaido Univ.)
3rd Author's Name Hiroyasu Ando
3rd Author's Affiliation University of Tsukuba(Univ. of Tsukuba)
Date 2019-08-02
Paper # CCS2019-23
Volume (vol) vol.119
Number (no) CCS-157
Page pp.pp.27-30(CCS),
#Pages 4
Date of Issue 2019-07-25 (CCS)