Presentation 2018-05-19
On Stability of Sparse Binary Neural Networks
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 ternary connection parameters and the signum activaion function. Depending on connection parameters, the network can generate various binary periodic orbits. This paper studies stability of desired periodic orbits and hardware designs of the network. First, we define local stability of periodic orbits and investigate relationship between connection sparsity and local stability. Second, using Verilog HDL, an elementary FPGA circuit of the network is desgined. Third, a class of general dimensional network is presented for theoretical stability analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Dynamic binary neural networks / Associative memories / Periodic orbits / Stability
Paper # NC2018-3
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 Stability of Sparse Binary Neural Networks
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 2018-05-19
Paper # NC2018-3
Volume (vol) vol.118
Number (no) NC-45
Page pp.pp.9-13(NC),
#Pages 5
Date of Issue 2018-05-12 (NC)