浏览全部资源
扫码关注微信
清华大学化学工程系!北京100084,清华大学化学工程系!北京100084,清华大学化学工程系,北京,100084
网络首发:1996-06-25,
纸质出版:1996-06-25
移动端阅览
陈方泽, 陈丙珍, 何小荣. 遗传算法与神经网络(Ⅰ)──用改进的遗传算法训练神经网络[J]. 化工学报, 1996,(3).
Chen Fangze, Chen Bingzhen, He Xiaorong(Department of Chemical Engineering. GENETIC ALGORITHMS AND ARTIFICIAL NEURAL NETWORK(Ⅰ)──TRAINING ARTIFICIAL NEURAL NETWORK WITH EXTENDED GENETIC ALGORITHMS[J]. CIESC Journal, 1996, (3).
陈方泽, 陈丙珍, 何小荣. 遗传算法与神经网络(Ⅰ)──用改进的遗传算法训练神经网络[J]. 化工学报, 1996,(3). DOI:
Chen Fangze, Chen Bingzhen, He Xiaorong(Department of Chemical Engineering. GENETIC ALGORITHMS AND ARTIFICIAL NEURAL NETWORK(Ⅰ)──TRAINING ARTIFICIAL NEURAL NETWORK WITH EXTENDED GENETIC ALGORITHMS[J]. CIESC Journal, 1996, (3). DOI:
针对BP(backpropagation)神经网络训练中的局部最优问题,提出了由改进的遗传算法EGA训练BP神经网络的新方法.该方法克服了经典遗传算法的不足,通过自适应多点变异操作比较有效地克服了收敛过程中的振荡问题,因而提高了BP网络训练的速度,并且找到了合理的变异因子范围.
In order to overcome a local optimal solution which often occurs in the training process of artificial neural networks
a new algorithm called EGA is proposed.An adaptive multipoint mutation operator
which can effectively extinguish the swing problem in convergent process
is proposed in this algorithm.So the speed of BP training is improved.A reasonable mutation factor range is found.As a result
the speed and accuracy of training artificial neural networks are much improved.
0
浏览量
515
下载量
CSCD
关联资源
相关文章
相关作者
相关机构