%0 Journal Article
%T Study on improving the convergence of genetic neural networks<br>改善遗传神经网络收敛性的研究
%A LI Xiang-mei
%A ZHAO Tian-yun
%A <br>李享梅
%A 赵天昀
%J 计算机应用
%D 2005
%I 
%X To describe the advantage and shortcoming of gradient descent algorithm and genetic algorithm for training connection weights of neural networks,a new algorithm combined genetic algorithm with gradient descent algorithm was proposed,referred as to Hybrid Intelligence learning algorithm(HI).Applied to the problem of optimizing the connection weight of the feedforward neural networks,the algorithm was feasible.The design and realization of HI was introduced.And it was proved that hybrid intelligence learning algorithm is better,faster and more accurate than gradient descent algorithm and genetic algorithm in theory and practice.
%K Genetic Algorithms(GA)
%K GA neural networks
%K artificial neural networks
%K BP neural network
%K gradient descent algorithm
%K HI algorithms(Hybrid Intelligence learning algorithm)<br>遗传算法
%K 遗传神经网络
%K 人工神经网络
%K BP神经网络
%K 梯度下降法
%K 混合智能学习法
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=FA63FAB4554C92C1&yid=2DD7160C83D0ACED&vid=C5154311167311FE&iid=59906B3B2830C2C5&sid=8506E11B7A5975B6&eid=B92DA4008CEC559E&journal_id=1001-9081&journal_name=计算机应用&referenced_num=0&reference_num=13