A Sparse Target Matrix Generation Based Unsupervised Feature Learning Algorithm for Image Classification

최초 등록일
2018.10.03
최종 저작일
2018.10
20페이지/파일확장자 어도비 PDF
가격 5,500원 할인쿠폰받기
판매자한국학술정보(주)
다운로드
장바구니
자격시험 이용후기 이벤트

* 본 문서는 배포용으로 복사 및 편집이 불가합니다.

서지정보

발행기관 : 한국인터넷정보학회 수록지정보 : KSII Transactions on Internet and Information Systems (TIIS) / 12권 / 6호
저자명 : ( Dan Zhao ) , ( Baolong Guo ) , ( Yunyi Yan )

영어 초록

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm (L<sub>2</sub>) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.

참고 자료

없음

자료문의

제휴사는 별도로 자료문의를 받지 않고 있습니다.

판매자 정보

한국학술정보(주)는 콘텐츠 제작에 도움이 되는 솔루션을 기반으로 풍부한 문화 콘텐츠를 생성하여 새로운 삶의 가치를 창조합니다.

본 학술논문은 한국학술정보(주)와 각 학회간에 저작권계약이 체결된 것으로 AgentSoft가 제공 하고 있습니다.
본 저작물을 불법적으로 이용시는 법적인 제재가 가해질 수 있습니다.

찾던 자료가 아닌가요?아래 자료들 중 찾던 자료가 있는지 확인해보세요

더보기
우수 콘텐츠 서비스 품질인증 획득
최근 본 자료더보기
A Sparse Target Matrix Generation Based Unsupervised Feature Learning Algorithm for Image Classification