基于填充函数的深度学习优化算法  

作　　者：叶成 吕柏权[1] 倪陈龙 

机构地区：[1]上海大学机电工程与自动化学院

出　　处：《工业控制计算机》2019年第10期113-115,共3页Industrial Control Computer

摘　　要：提出了基于填充函数的深度学习优化算法,深度学习采用的是分层的训练机制,它通过最小化误差函数进行分层的无监督训练。第一步先使用无标签的训练样本对各层参数分层预训练,第二步使用有标签的训练样本对各层参数进行微调,从而有利于减少陷入局部极小点的可能性。另外,引进了填充函数法,使之能够跳出局部最小值,继续迭代至更小的极值点,得到精度更高的全局最优点。通过对5个基准测试函数进行仿真和统计数据,验证了改进后算法的有效性。This paper proposes a depth learning optimization algorithm based on filling function.Depth learning adopts a layered training mechanism,which carries out layered unsupervised training by minimizing error function.In the first step,unlabeled training samples are used to conduct stratified pre-training for each layer of parameters;in the second step,labeled training samples are used to fine-tune the parameters of each layer.This helps to reduce the possibility of falling into local minima.In addition,the method of filling function is introduced,which makes it possible to jump out of the local minimum and continue to iterate to the smaller extreme point,thus obtaining the global optimum with higher precision.In this paper,through the simulation of five benchmark functions and their statistical data,the improved algorithm is verified to be validated.

关 键 词：填充函数 全局最优值 深度学习 

分 类 号：G63[文化科学—教育学]