Presentation 2018-01-27
Stability and periodic orbits in dynamic binary neural newtorks
Seitaro Koyama, Shunsuke Aoki, Toshimichi Saito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The dynamic binary neural network is characterized by the signum activation function and ternary connection parameters. Depending on the parameters, the network can generate various binary periodic orbits. This paper analyzes the dynamics of typical network examples. In order to analyze the dynamics, we introduce the two feature quantities which characterize stability and one-bit error correction of periodic orbits. We consider the relationship between the number the cells and stability of periodic orbits. In some sparse network, as the number of the cells increases, stability of periodic orbits tends to be weak.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Dynamic binary neural networks / Associative memories / Periodic orbits / Stability
Paper # NLP2017-97
Date of Issue 2018-01-19 (NLP)

Conference Information
Committee MBE / NC / NLP
Conference Date 2018/1/26(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyushu Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) ME, generalImplementation of Neuro Computing,Analysis and Modeling of Human Science,
Chair Kazuki Nakajima(Univ. of Toyama) / Masafumi Hagiwara(Keio Univ.) / Masaharu Adachi(Tokyo Denki Univ.)
Vice Chair Masaki Kyoso(TCU) / Yutaka Hirata(Chubu Univ.) / Norikazu Takahashi(Okayama Univ.)
Secretary Masaki Kyoso(Toyama Pref. Univ.) / Yutaka Hirata(Kindai Univ.) / Norikazu Takahashi(Tokyo Inst. of Tech.)
Assistant Kim Juhyon(Univ. of Toyama) / Takumi Kobayashi(YNU) / Yoshihisa Shinozawa(Keio Univ.) / Keiichiro Inagaki(Chubu Univ.) / Toshihiro Tachibana(Shonan Inst. of Tech.) / Masayuki Kimura(Kyoto Univ.)

Paper Information
Registration To Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing / Technical Committee on Nonlinear Problems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stability and periodic orbits in dynamic binary neural newtorks
Sub Title (in English)
Keyword(1) Dynamic binary neural networks
Keyword(2) Associative memories
Keyword(3) Periodic orbits
Keyword(4) Stability
1st Author's Name Seitaro Koyama
1st Author's Affiliation Hosei University(HU)
2nd Author's Name Shunsuke Aoki
2nd Author's Affiliation Hosei University(HU)
3rd Author's Name Toshimichi Saito
3rd Author's Affiliation Hosei University(HU)
Date 2018-01-27
Paper # NLP2017-97
Volume (vol) vol.117
Number (no) NLP-415
Page pp.pp.59-62(NLP),
#Pages 4
Date of Issue 2018-01-19 (NLP)