基于极限学习机的迁移学习算法  

A Transfer Learning Algorithm Based on Extreme Learning Machine

作　　者：金培源 金杭森 高波涌 陆慧娟 JIN Peiyuan;JIN Hangsen;GAO Boyong;LU Huijuan(College of Information Engineering,China Jiliang University,Hangzhou 310018,China;Xi'an Institute of Electromechanical Information Technology,Xi'an 710065,China)

机构地区：[1]中国计量大学信息工程学院,浙江杭州310018 [2]西安机电信息技术研究所,陕西西安710065

出　　处：《探测与控制学报》2020年第6期77-80,共4页Journal of Detection & Control

基　　金：国家自然科学基金项目资助(61272315,60842009);浙江省自然科学基金项目资助(LY12H29012,Y1110342)。

摘　　要：针对机器学习算法在类不平衡的数据集上容易受到选择性偏差的影响,提出了一种基于极限学习机(ELM)的迁移学习算法。该算法旨在利用大量已标签的源领域数据与只有少量样本的目标域数据之间的相关性,通过计算源域与目标域中的输出权值来实现两域间的迁移学习,从而提升迁移学习对非平衡样本的学习能力。实验结果表明,该方法对普林斯顿三维模型库数据具有良好的分类效果及不错的稳定性。Since the imbalance data would tend to suffer from the effect of sample selection bias,an improved transfer learning algorithm based on Extreme Learning Machine(ELM)was proposed.This algorithm is aimed to use the correlation between plenty of labeled source domain data and target domain data with few samples to find out the related samples,by calculating the output weights in the source domain and the target domain respectively to achieve the transfer learning between the two domains,so as to improve the transfer learning s performance on imbalance data.The experimental results show the algorithm has better classification results and good stability on the Princeton 3D Shape Benchmark Database.

关 键 词：迁移学习 极限学习机 三维模型分类 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]