Presentation 2019-06-17
Analysis and application of periodic orbits in dynamic binary neural networks
Shota Anzai, Seitaro Koyama, Toshimichi Saito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies a simple dynamic binary neural network and its application. In the network, each neuron transforms tree binary inputs to one binary outputs via the signum activation function: the network is characterized by sparse connection of the local binary connection. Depending on the parameters and initial condition, the network can generate various binary periodic orbits. The sparse connection is suitable for FPGA based hardware implementation and precise numerical analysis. First, we give parameters conditions that guarantee storage of a desired periodic orbit and its local stability. Second, we consider two typical examples of periodic orbits based on the insect walking gaits. Switching between the two periodic orbits is also considered. Suitable parameters of the network is given after trial-and-errors. Third, applying Verilog simulation, a test circuit of the network is designed and generation of the periodic orbits is confirmed. These results will be developed into application to an FPGA based hardware of central pattern generators.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) binary neural networks / sparsity / central pattern generators
Paper # NC2019-1
Date of Issue 2019-06-10 (NC)

Conference Information
Committee NC / IBISML / IPSJ-MPS / IPSJ-BIO
Conference Date 2019/6/17(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Okinawa Institute of Science and Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Neurocomputing, Machine Learning Approach to Biodata Mining, and General
Chair Hayaru Shouno(UEC) / Hisashi Kashima(Kyoto Univ.) / Masakazu Sekijima(Tokyo Tech) / Hiroyuki Kurata(Kyutech)
Vice Chair Kazuyuki Samejima(Tamagawa Univ) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Kazuyuki Samejima(NAIST) / Masashi Sugiyama(NTT) / Koji Tsuda(Nagoya Inst. of Tech.) / (AIST) / (Nagoya Univ.)
Assistant Takashi Shinozaki(NICT) / Ken Takiyama(TUAT) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / IPSJ Special Interest Group on Mathematical Modeling and Problem Solving / IPSJ Special Interest Group on Bioinformatics and Genomics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analysis and application of periodic orbits in dynamic binary neural networks
Sub Title (in English)
Keyword(1) binary neural networks
Keyword(2) sparsity
Keyword(3) central pattern generators
1st Author's Name Shota Anzai
1st Author's Affiliation HOSEI University(HU)
2nd Author's Name Seitaro Koyama
2nd Author's Affiliation HOSEI University(HU)
3rd Author's Name Toshimichi Saito
3rd Author's Affiliation HOSEI University(HU)
Date 2019-06-17
Paper # NC2019-1
Volume (vol) vol.119
Number (no) NC-88
Page pp.pp.1-1(NC),
#Pages 1
Date of Issue 2019-06-10 (NC)