A one-layer dual neural network with a unipolar hard-limiting activation function for shortest-path routing
Refereed conference paper presented and published in conference proceedings

香港中文大學研究人員
替代計量分析
.

其它資訊
摘要The shortest path problem is an archetypal combinatorial optimization problem arising in a variety of application settings. For real-time applications, parallel computational approaches such as neural computation are more desirable. This paper presents a new recurrent neural network with a simple structure for solving the shortest path problem (SPP). Compared with the existing neural networks for SPP, the proposed neural network has a lower model complexity; i.e., the number of neurons in the neural network is the same as the number of nodes in the problem. A simple lower bound on the gain parameter is derived to guarantee the finite-time global convergence of the proposed neural network. The performance and operating characteristics of the proposed neural network are demonstrated by means of simulation results. © 2010 Springer-Verlag Berlin Heidelberg.
著者Liu Q., Wang J.
會議名稱20th International Conference on Artificial Neural Networks, ICANN 2010
會議開始日15.09.2010
會議完結日18.09.2010
會議地點Thessaloniki
會議國家/地區希臘
詳細描述organized by Springer Lecture Notes in Computer Science, vol. 6353,
出版年份2010
月份11
日期8
卷號6353 LNCS
期次PART 2
出版社Springer Verlag
出版地Germany
頁次498 - 505
國際標準書號3642158218
國際標準期刊號0302-9743
語言英式英語

上次更新時間 2021-27-02 於 00:10