计算机与数字工程2018，Vol.46Issue(5)：857-860,4.DOI:10.3969/j.issn.1672-9722.2018.05.002
基于ELM-AE的迁移学习算法
Domain Adaption Algorithm Based on ELM Autoencoder
摘要
Abstract
ELM Autoencoder(ELM-AE)can extract data features,a new domain adaption algorithm is designed based on ELM-AE,which describe the subspaces of source and target domain by ELM-AE,and then subspace alignment is carryed out to project different domains into a common new space.The widely experimental results on Office[1]/Caltech256[2]data sets show that the proposed algorithm can achieve better classification accuracy than other state-of-art transfer learning algorithms in most cases.关键词
ELM-AE/子空间/子空间对齐/迁移学习Key words
ELM-AE/subspace/subspace alignment/domain adaption分类
信息技术与安全科学引用本文复制引用
邓万宇,屈玉涛,张倩..基于ELM-AE的迁移学习算法[J].计算机与数字工程,2018,46(5):857-860,4.基金项目
国家自然科学基金项目(编号:61572399) （编号:61572399）
陕西省青年科技新星项目(编号:2013KJXX-29)资助. （编号:2013KJXX-29）
