Presentation 2023-03-15
On binary periodic orbits in sparse binary neural networks
Hiroki Nonaka, Toshimichi Saito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies periodic orbits in a dynamic binary neural network constructed by the signum activation function and sparse binary connection. The dynamics is described by an autonomous difference equation of binary state variables. Depending on the connection parameters, the network exhibits a variety of rotation-type periodic orbits of binary vectors. In the network, we present simple parameter setting method that guarantees generation of typical periodic orbits. Applying precise numerical/theoretical analysis, the number and stability of the periodic orbits are clarified. Presenting a simple FPGA based hardware prototype, typical periodic orbits are confirmed experimentally. The hardware will be developed into engineering applications including control systems of switching circuits and walking robots.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) reccurent neural networks / binary neural networks / periodic orbits / stability / FPGA
Paper # MSS2022-71,NLP2022-116
Date of Issue 2023-03-08 (MSS, NLP)

Conference Information
Committee NLP / MSS
Conference Date 2023/3/15(3days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Akio Tsuneda(Kumamoto Univ.) / Atsuo Ozaki(Osaka Inst. of Tech.)
Vice Chair Hiroyuki Torikai(Hosei Univ.) / Shingo Yamaguchi(Yamaguchi Univ.)
Secretary Hiroyuki Torikai(Sojo Univ.) / Shingo Yamaguchi(Gifu Univ.)
Assistant Yuichi Yokoi(Nagasaki Univ.) / Yoshikazu Yamanaka(Utsunomiya Univ.) / Masato Shirai(Shimane Univ.)

Paper Information
Registration To Technical Committee on Nonlinear Problems / Technical Committee on Mathematical Systems Science and its Applications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On binary periodic orbits in sparse binary neural networks
Sub Title (in English)
Keyword(1) reccurent neural networks
Keyword(2) binary neural networks
Keyword(3) periodic orbits
Keyword(4) stability
Keyword(5) FPGA
1st Author's Name Hiroki Nonaka
1st Author's Affiliation Hosei University(HU)
2nd Author's Name Toshimichi Saito
2nd Author's Affiliation Hosei University(HU)
Date 2023-03-15
Paper # MSS2022-71,NLP2022-116
Volume (vol) vol.122
Number (no) MSS-435,NLP-436
Page pp.pp.49-52(MSS), pp.49-52(NLP),
#Pages 4
Date of Issue 2023-03-08 (MSS, NLP)