计算机工程与应用2011，Vol.47Issue(2)：29-31,3.DOI:10.3778/j.issn.1002-8331.2011.02.009
幂激励前向神经网络最优结构确定算法
Optimal-structure determination of power-activation feed-forward neural net
摘要
Abstract
For a kind of feed-forward neural net with hidden-neurons' activation-functions being a sequence of power functions, an optimal network-structure determination algorithm is proposed based on the weights-direct-determination method.Computer simulation and verification results indicate that the algorithm can determine the optimal number of hidden-layer neurons automatically, quickly and effectively, which achieves the best approximation ability of the neural net and thus realizes the network-structure optimization.关键词
幂级数/前向神经网络/隐神经元数/结构最优化/权值直接确定法Key words
power series/ feed-forward neural net/ hidden-layer neurons/ structure optimization/ weights direct determination分类
信息技术与安全科学引用本文复制引用
张雨浓,郭东生,谭宁..幂激励前向神经网络最优结构确定算法[J].计算机工程与应用,2011,47(2):29-31,3.基金项目
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60775050) （the National Natural Science Foundation of China under Grant No.60775050）
国家教育部新世纪人才支持计划(the New Century Excellent Talent Foundation from MOE of China under Grant No.NCET-07-0887) （the New Century Excellent Talent Foundation from MOE of China under Grant No.NCET-07-0887）
教育部留学回国人员科研启动基金(The Project-sponsored by SRF for ROCS,SEM No.4105337). （The Project-sponsored by SRF for ROCS,SEM No.4105337）
