%0 Journal Article
%T Structure Optimization for Feed-forward Neural Networks Based on Evolutionary Programming and Sequential Quadratic Programming<br>利用进化规划和逐步二次规划实现前馈神经网络的结构优化
%A JIN Cong
%A <br>金聪
%J 系统工程理论与实践
%D 2003
%I 
%X In this paper, when evolutionary programming and sequential quadratic programming are applied to the structure optimization of feed-forward neural networks, a learning algorithm is proposed. The new algorithm retains the ability of stochastic global searching. It has better global convergence and very strong self-adaptive ability with environment. The efficiency of research work mentioned above has been shown by simulation and applications.
%K feed-forward neural networks
%K evolutionary programming
%K structure optimization
%K sequential quadratic programming<br>前馈神经网络
%K 进化规划
%K 结构优化
%K 逐步二次规划
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=01BA20E8BA813E1908F3698710BBFEFEE816345F465FEBA5&cid=962324E222C1AC1D&jid=1D057D9E7CAD6BEE9FA97306E08E48D3&aid=68A5AFC6C6F45B11&yid=D43C4A19B2EE3C0A&vid=EA389574707BDED3&iid=0B39A22176CE99FB&sid=F24949CFDB502409&eid=4DB1E72614E68564&journal_id=1000-6788&journal_name=系统工程理论与实践&referenced_num=5&reference_num=9