基于遗传模拟退火算法优化的BP神经网络
|
摘要
在研究标准BP神经网络的基础上,针对其存在的收敛速度慢、且容易陷入局部极小值等问题进行分析,设计实现一种采用数值优化的方法来改进BP网络性能的新的混合神经网络模型。通过引入遗传模拟退火算法扩大了网络的权值更新空间,把得到最优权值赋予BP神经网络,从而使优化后的神经网络具有泛化性好,不易陷入局部极小值等优点。与标准BP神经网络进行比较,仿真结果表明,该网络模型能够达到比较高的分类精度。
After studying the disadvantage of BP neural network which has low convergent speed and trap into local minima easily,an idea of designing a new hybrid neural network model which adopts the method of numerical optimization is presented.By using Genetic-Stimulated Annealing algorithm(GSA),expands the updated space of weight.On the basis,it makes the acquired better value as the weight of BP neural network,and the optimized BP network is not easy to trap into the local minima and has good generalization characteristic.Making the comparation GSA network with standard BP network,simulation analysis demonstrates that this network model can attain higher categories of precision.
After studying the disadvantage of BP neural network which has low convergent speed and trap into local minima easily,an idea of designing a new hybrid neural network model which adopts the method of numerical optimization is presented.By using Genetic-Stimulated Annealing algorithm(GSA),expands the updated space of weight.On the basis,it makes the acquired better value as the weight of BP neural network,and the optimized BP network is not easy to trap into the local minima and has good generalization characteristic.Making the comparation GSA network with standard BP network,simulation analysis demonstrates that this network model can attain higher categories of precision.
引文
[1]张国栋,雷晓玲,彭宏.基于BP神经网络的环境质量评估[J].长沙理工大学学报,2004,2(4):93-96.
[2]杨居易,易永宏.基于BP神经网络的地震预测研究[J].微电子学与计算机,2008,25(10):129-132.
[3]王国峰,王殿辉,周亦武,等.BP神经网络在溶液浓度检测中的应用[J].大连海事大学学报,2001,27(1):89-92.
[4]Zhang Y,Wang J.Obstacle avoidance of kinematically re-dundant manipulators using a dual neural network[J].IEEE Transactions on Systems,Man,and Cybernetics,2004,34(1):752-759.
[5]周昌能,余雪丽.基于BP网络的权值更新快速收敛算法[J].计算机应用,2006,26(8):1940-1942.
[6]Meissner M,Schmuker,Schneider G.Optimized Particle SwarmOptimization(OPSO)and its application to artificial neuralnetwork training[J].BMC Bioinformatics,2006,7(1):125-136.
[7]Martin THagan,Howard B Demuth,Mark HBeale.神经网络设计[M].戴葵译.北京:机械工业出版社,2002:236-238.
[8]陈华根,吴健生,王家林,等.模拟退火算法机理研究[J].同济大学学报:自然科学版,2004,32(6):802-805.
[9]马成前,王庆喜.基于局部及全局误差的BP神经网络研究[J].武汉理工大学学报,2009,31(20):99-101.
[10]田雨波.混合神经网络技术[M].北京:科学出版社,2009:38-40.
[11]Ito Y.Representation of functions by superposition of a stepor sigmoidal function and their application to neural net-work theory[J].Neural Networks,1991,4(3):385-394.
[12]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999:79-80.
[13]赵仕俊,孙美玲,唐懿芳.基于遗传模拟退火算法的无线传感器网络定位算法[J].计算机应用与软件,2009,26(10):189-192.
[14]杜宗宗,刘国栋.基于混合遗传模拟退火算法求解TSP问题[J].计算机工程与应用,2010,29(2):179-183.
[15]Forina M.UC Irvine Machine Learning Repository[DB/OL].http://archive.ics.uci.edu./ml/datasets/wine,1991-07-01.
[2]杨居易,易永宏.基于BP神经网络的地震预测研究[J].微电子学与计算机,2008,25(10):129-132.
[3]王国峰,王殿辉,周亦武,等.BP神经网络在溶液浓度检测中的应用[J].大连海事大学学报,2001,27(1):89-92.
[4]Zhang Y,Wang J.Obstacle avoidance of kinematically re-dundant manipulators using a dual neural network[J].IEEE Transactions on Systems,Man,and Cybernetics,2004,34(1):752-759.
[5]周昌能,余雪丽.基于BP网络的权值更新快速收敛算法[J].计算机应用,2006,26(8):1940-1942.
[6]Meissner M,Schmuker,Schneider G.Optimized Particle SwarmOptimization(OPSO)and its application to artificial neuralnetwork training[J].BMC Bioinformatics,2006,7(1):125-136.
[7]Martin THagan,Howard B Demuth,Mark HBeale.神经网络设计[M].戴葵译.北京:机械工业出版社,2002:236-238.
[8]陈华根,吴健生,王家林,等.模拟退火算法机理研究[J].同济大学学报:自然科学版,2004,32(6):802-805.
[9]马成前,王庆喜.基于局部及全局误差的BP神经网络研究[J].武汉理工大学学报,2009,31(20):99-101.
[10]田雨波.混合神经网络技术[M].北京:科学出版社,2009:38-40.
[11]Ito Y.Representation of functions by superposition of a stepor sigmoidal function and their application to neural net-work theory[J].Neural Networks,1991,4(3):385-394.
[12]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999:79-80.
[13]赵仕俊,孙美玲,唐懿芳.基于遗传模拟退火算法的无线传感器网络定位算法[J].计算机应用与软件,2009,26(10):189-192.
[14]杜宗宗,刘国栋.基于混合遗传模拟退火算法求解TSP问题[J].计算机工程与应用,2010,29(2):179-183.
[15]Forina M.UC Irvine Machine Learning Repository[DB/OL].http://archive.ics.uci.edu./ml/datasets/wine,1991-07-01.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心