有指导机器学习超参数的交叉验证智能优化  

Intelligent Optimization of Hyper-Parameters of Supervised Machine Learning Based on Cross Validation

作　　者：李刚[1] 高武奇[2] 杨瑞臣[3] LI Gang GAO Wuqi YANG Ruichen(School of Economics and Management, Xi ＇ an Technological University, Xi＇ an 710021, China School of Computer Science and Engineering, Xi＇ an Technological University, Xi＇ an 710021, China Department of Social Science and Mathematics ＆ Physics,Chengde Petroleum College,Chengde 067000,China)

机构地区：[1]西安工业大学经济与管理学院,西安710021 [2]西安工业大学计算机科学与工程学院,西安710021 [3]承德石油高等专科学校社科与数理部,承德067000

出　　处：《西安工业大学学报》2016年第11期906-910,共5页Journal of Xi’an Technological University

基　　金：承德市科学技术研究与发展计划项目(20153021);陕西省普通高等学校哲学社会科学特色学科建设项目;西安工业大学科研创新团队建设计划

摘　　要：不合理的模型超参数会导致有指导机器学习过拟合或欠拟合,文中提出模型超参数的交叉验证智能优化方法:利用交叉验证评价不同参数下的学习性能,在此基础之上构建智能寻优技术路线.实验结果表明:利用交叉验证性目标函数,智能优化算法自适应地根据目标函数和约束求解,可高效、准确地优化学习器超参数.Unreasonable hyper-parameters lead the supervised machine learning to over-fitting or under -fitting. The paper presents a cross validation intelligent optimization of hyper-parameters. The cross validation is used to evaluate learning performance under the different parameters, on the basis of which the technical path of intelligent optimization is determined. Experimental results show that, by using the cross validation objective function,the intelligent optimization algorithm finds the best hyper-parameters efficiently and accurately according to the objective function and constraints adaptively.

关 键 词：交叉验证 有指导学习 模型选择 智能优化 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]