A high order neural network to solve N-queens problem

Yuxin Ding; Ye Li; Min Xiao; Qing Wang; Dong Li

doi:10.1109/IJCNN.2010.5596706

A high order neural network to solve N-queens problem

Yuxin Ding^*
, Ye Li
, Min Xiao
, Qing Wang
, Dong Li

^*Corresponding author for this work

School of Computer Science and Technology

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

High order hopfield network has a higher store capacity and a faster convergence speed compared with the first order hopfield network. However, in optimization field, such as combination optimization field, high order network is seldom to be used. So how to construct high order network to solve these problem is an interesting problem. In this paper a new kind of high order discrete hopfield neural network is proposed to solve N-queens problem. The construction method of energy function is given and the neural computing method is shown. It is also discussed the method how to speed the convergence and escape from local minima. Compared with the first order hopfield network, experimental results show high order network has a quick convergence speed, the performance of high order network is better than the discrete Hopfield network.

Original language	English
Title of host publication	2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Print)	9781424469178
DOIs	https://doi.org/10.1109/IJCNN.2010.5596706
State	Published - 2010
Event	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 - Barcelona, Spain Duration: 18 Jul 2010 → 23 Jul 2010

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Conference

Conference	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
Country/Territory	Spain
City	Barcelona
Period	18/07/10 → 23/07/10

Access to Document

10.1109/IJCNN.2010.5596706

Cite this

Ding, Y., Li, Y., Xiao, M., Wang, Q., & Li, D. (2010). A high order neural network to solve N-queens problem. In 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 Article 5596706 (Proceedings of the International Joint Conference on Neural Networks). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2010.5596706

@inproceedings{0e0d7b01f3a040ff8e10f884bfea3137,

title = "A high order neural network to solve N-queens problem",

abstract = "High order hopfield network has a higher store capacity and a faster convergence speed compared with the first order hopfield network. However, in optimization field, such as combination optimization field, high order network is seldom to be used. So how to construct high order network to solve these problem is an interesting problem. In this paper a new kind of high order discrete hopfield neural network is proposed to solve N-queens problem. The construction method of energy function is given and the neural computing method is shown. It is also discussed the method how to speed the convergence and escape from local minima. Compared with the first order hopfield network, experimental results show high order network has a quick convergence speed, the performance of high order network is better than the discrete Hopfield network.",

author = "Yuxin Ding and Ye Li and Min Xiao and Qing Wang and Dong Li",

year = "2010",

doi = "10.1109/IJCNN.2010.5596706",

language = "英语",

isbn = "9781424469178",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010",

address = "美国",

note = "2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 ; Conference date: 18-07-2010 Through 23-07-2010",

}

Ding, Y, Li, Y, Xiao, M, Wang, Q & Li, D 2010, A high order neural network to solve N-queens problem. in 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010., 5596706, Proceedings of the International Joint Conference on Neural Networks, Institute of Electrical and Electronics Engineers Inc., 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010, Barcelona, Spain, 18/07/10. https://doi.org/10.1109/IJCNN.2010.5596706

A high order neural network to solve N-queens problem. / Ding, Yuxin; Li, Ye; Xiao, Min et al.
2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010. Institute of Electrical and Electronics Engineers Inc., 2010. 5596706 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A high order neural network to solve N-queens problem

AU - Ding, Yuxin

AU - Li, Ye

AU - Xiao, Min

AU - Wang, Qing

AU - Li, Dong

PY - 2010

Y1 - 2010

N2 - High order hopfield network has a higher store capacity and a faster convergence speed compared with the first order hopfield network. However, in optimization field, such as combination optimization field, high order network is seldom to be used. So how to construct high order network to solve these problem is an interesting problem. In this paper a new kind of high order discrete hopfield neural network is proposed to solve N-queens problem. The construction method of energy function is given and the neural computing method is shown. It is also discussed the method how to speed the convergence and escape from local minima. Compared with the first order hopfield network, experimental results show high order network has a quick convergence speed, the performance of high order network is better than the discrete Hopfield network.

AB - High order hopfield network has a higher store capacity and a faster convergence speed compared with the first order hopfield network. However, in optimization field, such as combination optimization field, high order network is seldom to be used. So how to construct high order network to solve these problem is an interesting problem. In this paper a new kind of high order discrete hopfield neural network is proposed to solve N-queens problem. The construction method of energy function is given and the neural computing method is shown. It is also discussed the method how to speed the convergence and escape from local minima. Compared with the first order hopfield network, experimental results show high order network has a quick convergence speed, the performance of high order network is better than the discrete Hopfield network.

UR - https://www.scopus.com/pages/publications/79959447597

U2 - 10.1109/IJCNN.2010.5596706

DO - 10.1109/IJCNN.2010.5596706

M3 - 会议稿件

AN - SCOPUS:79959447597

SN - 9781424469178

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010

Y2 - 18 July 2010 through 23 July 2010

ER -

Ding Y, Li Y, Xiao M, Wang Q, Li D. A high order neural network to solve N-queens problem. In 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010. Institute of Electrical and Electronics Engineers Inc. 2010. 5596706. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2010.5596706

A high order neural network to solve N-queens problem

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this