COMPARISONS OF 7 NEURAL-NETWORK MODELS ON TRAFFIC CONTROL-PROBLEMS IN MULTISTAGE INTERCONNECTION NETWORKS

被引：14

作者：

FUNABIKI, N

TAKEFUJI, Y

LEE, KC

机构：

[1] CASE WESTERN RESERVE UNIV, DEPT ELECT ENGN & APPL PHYS, CLEVELAND, OH 44106 USA

[2] KEIO UNIV, FAC ENVIRONM INFORMAT, TOKYO 108, JAPAN

[3] CIRRUS LOG INC, DEPT R&D, FREMONT, CA 94538 USA

来源：

IEEE TRANSACTIONS ON COMPUTERS | 1993年 / 42卷 / 04期

关键词：

DECAY TERM; HYSTERESIS MCCULLOCH-PITTS NEURON MODEL; MCCULLOCH-PITTS NEURON MODEL; MULTISTAGE INTERCONNECTION NETWORK; NEURAL NETWORK; OPTIMIZATION; PARALLEL ALGORITHM; SIGMOID NEURON MODEL;

D O I：

10.1109/12.214695

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents performance comparisons of seven neural network models on traffic control problems in multistage interconnection networks. The decay term, three neuron models, and two heuristics were evaluated. The goal of the traffic control problems is to find conflict-free switching configurations with the maximum throughput. Our simulation results show that the hysteresis McCulloch-Pitts neuron model without the decay term and with two heuristics has the best performance.

引用

页码：497 / 501

页数：5

共 18 条

[1]

Batcher K. E., 1976, Proceedings of the 1976 International Conference on Parallel Processing, P65

[2] NEURAL NETWORK DESIGN OF A BANYAN NETWORK CONTROLLER [J].