The search functionality is under construction.

The search functionality is under construction.

We propose hysteresis neural network solving combinatorial optimization problems, Box Puzzling Problem. Hysteresis neural network searches solutions of the problem with nonlinear dynamics. The output vector becomes stable only when it corresponds with a solution. This system does never become stable without satisfying constraints of the problem. After estimating hardware calculating time, we obtain that numerical calculating time increases extremely comparing with hardware time as problem's scale increases. However the system has possibility of limit cycle. Though it is very hard to remove limit cycle completely, we propose some methods to remove this phenomenon.

- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E84-A No.9 pp.2173-2181

- Publication Date
- 2001/09/01

- Publicized

- Online ISSN

- DOI

- Type of Manuscript
- Special Section PAPER (Special Section on Nonlinear Theory and its Applications)

- Category
- Application of Neural Network

The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.

Copy

Toshiya NAKAGUCHI, Shinya ISOME, Kenya JIN'NO, Mamoru TANAKA, "Box Puzzling Problem Solver by Hysteresis Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E84-A, no. 9, pp. 2173-2181, September 2001, doi: .

Abstract: We propose hysteresis neural network solving combinatorial optimization problems, Box Puzzling Problem. Hysteresis neural network searches solutions of the problem with nonlinear dynamics. The output vector becomes stable only when it corresponds with a solution. This system does never become stable without satisfying constraints of the problem. After estimating hardware calculating time, we obtain that numerical calculating time increases extremely comparing with hardware time as problem's scale increases. However the system has possibility of limit cycle. Though it is very hard to remove limit cycle completely, we propose some methods to remove this phenomenon.

URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e84-a_9_2173/_p

Copy

@ARTICLE{e84-a_9_2173,

author={Toshiya NAKAGUCHI, Shinya ISOME, Kenya JIN'NO, Mamoru TANAKA, },

journal={IEICE TRANSACTIONS on Fundamentals},

title={Box Puzzling Problem Solver by Hysteresis Neural Networks},

year={2001},

volume={E84-A},

number={9},

pages={2173-2181},

abstract={We propose hysteresis neural network solving combinatorial optimization problems, Box Puzzling Problem. Hysteresis neural network searches solutions of the problem with nonlinear dynamics. The output vector becomes stable only when it corresponds with a solution. This system does never become stable without satisfying constraints of the problem. After estimating hardware calculating time, we obtain that numerical calculating time increases extremely comparing with hardware time as problem's scale increases. However the system has possibility of limit cycle. Though it is very hard to remove limit cycle completely, we propose some methods to remove this phenomenon.},

keywords={},

doi={},

ISSN={},

month={September},}

Copy

TY - JOUR

TI - Box Puzzling Problem Solver by Hysteresis Neural Networks

T2 - IEICE TRANSACTIONS on Fundamentals

SP - 2173

EP - 2181

AU - Toshiya NAKAGUCHI

AU - Shinya ISOME

AU - Kenya JIN'NO

AU - Mamoru TANAKA

PY - 2001

DO -

JO - IEICE TRANSACTIONS on Fundamentals

SN -

VL - E84-A

IS - 9

JA - IEICE TRANSACTIONS on Fundamentals

Y1 - September 2001

AB - We propose hysteresis neural network solving combinatorial optimization problems, Box Puzzling Problem. Hysteresis neural network searches solutions of the problem with nonlinear dynamics. The output vector becomes stable only when it corresponds with a solution. This system does never become stable without satisfying constraints of the problem. After estimating hardware calculating time, we obtain that numerical calculating time increases extremely comparing with hardware time as problem's scale increases. However the system has possibility of limit cycle. Though it is very hard to remove limit cycle completely, we propose some methods to remove this phenomenon.

ER -