Presentation | 2019-10-22 Constraint Satisfaction Problem Solver by Hysteresis Neural Networks Takumi Genka, Kenya Jin'no, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Since solving Constraint Satisfaction Problems (CSPs) is very important, therefore, many solving methods are proposed. The solving method using artificial neural networks is one of such solving methods. In this article, we evaluate an actual calculation time to solve a constraint condition satisfaction problem by using our proposed hysteresis neural network (HNN) which was originally proposed in 1991. The HNN consists of a binary hysteresis neuron. The dynamics of each neuron is depended on the continuous state variable, and the output of the neuron takes two discrete values. The HNN is regarded as a piecewise linear system, and the solution trajectory of the HNN can be calculated rigorously and rapidly. We con- sider a solver by HNN for the four-coloring problem in this article. We investigate the actual calculation time of HNN solution search. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Constraint Satisfaction Problems / Neural Networks / four-coloring problem |
Paper # | CAS2019-24,NLP2019-64 |
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) | Constraint Satisfaction Problem Solver by Hysteresis Neural Networks |
Sub Title (in English) | |
Keyword(1) | Constraint Satisfaction Problems |
Keyword(2) | Neural Networks |
Keyword(3) | four-coloring problem |
1st Author's Name | Takumi Genka |
1st Author's Affiliation | Tokyo City University(Tokyo City Univ.) |
2nd Author's Name | Kenya Jin'no |
2nd Author's Affiliation | Tokyo City University(Tokyo City Univ.) |
Date | 2019-10-22 |
Paper # | CAS2019-24,NLP2019-64 |
Volume (vol) | vol.119 |
Number (no) | CAS-237,NLP-238 |
Page | pp.pp.7-10(CAS), pp.7-10(NLP), |
#Pages | 4 |
Date of Issue | 2019-10-15 (CAS, NLP) |