摘要
从学习率对BP网络误差下降曲线的影响机理入手,提出了能够使学习率具有自适应调整能力的有限监督调整方法,通过实证分析并结合实际工程算例阐明了该方法的有效性。
The mechanism of the impact of learning rate on the error-drop-curve of BP networks was studied. Then a limited supervising method for learning rate regulation was proposed, by which the learning rate of BP networks is capable for self-adaptive adjustment. This method was validated by demonstration study and engineering application.
出处
《吉林大学学报（工学版）》
EI
CAS
CSCD
北大核心
2007年第4期846-850,共5页
Journal of Jilin University:Engineering and Technology Edition
基金
国家自然科学基金资助项目(59809007)
关键词
人工智能
学习率
有限监督调整
人工神经网络
BP网络
artificial intelligence
learning rate
limited supervising to regulating
artificial neural network
BP networks
