教師資料查詢 | 類別: 期刊論文 | 教師: 許輝煌 Hsu Hui-huang (瀏覽個人網頁)

標題:Output Effect Evaluation Based on Input Features in Neural Incremental Attribute Learning for Better Classification Performance
學年103
學期1
出版(發表)日期2014/12/29
作品名稱Output Effect Evaluation Based on Input Features in Neural Incremental Attribute Learning for Better Classification Performance
作品名稱(其他語言)
著者Ting Wang; Guan, Sheng-Uei; Ka Lok Man; Jong Hyuk Park; Hsu, Hui-Huang
單位淡江大學資訊工程學系
出版者Basel: M D P I AG
著錄名稱、卷期、頁數Symmetry 7(1), pp.53-66
摘要Machine learning is a very important approach to pattern classification. This paper provides a better insight into Incremental Attribute Learning (IAL) with further analysis as to why it can exhibit better performance than conventional batch training. IAL is a novel supervised machine learning strategy, which gradually trains features in one or more chunks. Previous research showed that IAL can obtain lower classification error rates than a conventional batch training approach. Yet the reason for that is still not very clear. In this study, the feasibility of IAL is verified by mathematical approaches. Moreover, experimental results derived by IAL neural networks on benchmarks also confirm the mathematical validation.
關鍵字pattern classification;neural networks;incremental attribute learning;feature ordering;discrimination ability
語言英文
ISSN2073-8994
期刊性質國外
收錄於SCI;
產學合作
通訊作者
審稿制度
國別瑞士
公開徵稿
出版型式,電子版
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!