Presentation 2019-10-22
On transition from periodic orbits to fixed points in simple neural networks
Yuki Kawamura, Toshimichi Saito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A dynamic binary neural network is a recurrent-type neural networkcharacterized by cross-connection parameters and signum activation function. Depending on the parameters, the network can generate various binary periodic orbits. This paper studies transition from a target basic periodic orbit to a set of fixed points. Performing elementary numerical experiments, we have found two typical patterns. First, a target periodic orbit is changed into a set of fixed points via a periodic orbit with long period. Second, a target periodic orbit is changed into transient phenomena and is changed into a set of fixed points.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Dynamic binary neural networks / Periodic oebits
Paper # CAS2019-37,NLP2019-77
Date of Issue 2019-10-15 (CAS, NLP)

Conference Information
Committee NLP / CAS
Conference Date 2019/10/22(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Gifu Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Mathematical modeling, numerical simulation etc.
Chair Hiroaki Kurokawa(Tokyo Univ. of Tech.) / Taizo Yamawaki(Hitachi)
Vice Chair Kiyohisa Natsume(Kyushu Inst. of Tech.) / Yasuhiro Takashima(Univ. of Kitakyushu)
Secretary Kiyohisa Natsume(Nippon Inst. of Tech.) / Yasuhiro Takashima(Kyushu Inst. of Tech.)
Assistant Yutaka Shimada(Saitama Univ.) / Toshikaza Samura(Yamaguchi Univ.) / Hiroki Sato(Sony LSI Design) / Motoi Yamaguchi(Renesas Electronics)

Paper Information
Registration To Technical Committee on Nonlinear Problems / Technical Committee on Circuits and Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On transition from periodic orbits to fixed points in simple neural networks
Sub Title (in English)
Keyword(1) Dynamic binary neural networks
Keyword(2) Periodic oebits
1st Author's Name Yuki Kawamura
1st Author's Affiliation HOSEI University(HU)
2nd Author's Name Toshimichi Saito
2nd Author's Affiliation HOSEI University(HU)
Date 2019-10-22
Paper # CAS2019-37,NLP2019-77
Volume (vol) vol.119
Number (no) CAS-237,NLP-238
Page pp.pp.71-75(CAS), pp.71-75(NLP),
#Pages 5
Date of Issue 2019-10-15 (CAS, NLP)