摘要
llowing for the limitations of LS energy function used in BP algorithm, thispaper proposes a robust learning algorithm based on the study of how cluster-ing puts down radom noise’s effects and the consideration of intensified trainingfor high-quality examples. Some simulation results demonstrate that the robustalgorithm is clearly superior to BP algorithm in anti-disturbance and aJstringency.
llowing for the limitations of LS energy function used in BP algorithm, thispaper proposes a robust learning algorithm based on the study of how cluster-ing puts down radom noise's effects and the consideration of intensified trainingfor high-quality examples. Some simulation results demonstrate that the robustalgorithm is clearly superior to BP algorithm in anti-disturbance and aJstringency.
出处
《数值计算与计算机应用》
CSCD
北大核心
2000年第2期112-120,共9页
Journal on Numerical Methods and Computer Applications
基金
广东省重点学科项目!970003
广东省自然科学基金!960101
关键词
神经网络
鲁棒学习算法
噪声数据
noise, neural network, energy function, clustering, robustness,astringency
