微型机与应用
微型機與應用
미형궤여응용
MICROCOMPUTER & ITS APPLICATIONS
2009年
21期
7-9,15
,共4页
TSP问题%Hopfield网络%能量函数%遗传算法
TSP問題%Hopfield網絡%能量函數%遺傳算法
TSP문제%Hopfield망락%능량함수%유전산법
travel salesman problem(TSP)%Hopfield neural network%energy function%genetic algorithm
针对Hopfield网络求解TSP问题时出现无效解和收敛性能差的问题,对约束条件能量函数进行改进,构造了一种求解TSP问题的遗传Hopfield神经网络算法,并与经典Hopfield神经网络求解TSP方法进行对比.实验结果表明,本文算法具有更好的整体求解性能.
針對Hopfield網絡求解TSP問題時齣現無效解和收斂性能差的問題,對約束條件能量函數進行改進,構造瞭一種求解TSP問題的遺傳Hopfield神經網絡算法,併與經典Hopfield神經網絡求解TSP方法進行對比.實驗結果錶明,本文算法具有更好的整體求解性能.
침대Hopfield망락구해TSP문제시출현무효해화수렴성능차적문제,대약속조건능량함수진행개진,구조료일충구해TSP문제적유전Hopfield신경망락산법,병여경전Hopfield신경망락구해TSP방법진행대비.실험결과표명,본문산법구유경호적정체구해성능.
For the Hopfield network in solving traveling salesman problem often getting invalid and not optimal solution, an improved constrained optimization energy function is used as fitness function of the genetie algorithm. A solving traveling salesman problem algorithm based on the genetic Hopfield network is constructed. Compared with traditional Hopfield network algorithm, the solving algorithm in this paper can easy obtain effective global optimd solution is proved by simulation experiment results.
