Vui lòng dùng định danh này để trích dẫn hoặc liên kết đến tài liệu này:
http://repository-old.ntt.edu.vn/jspui/handle/298300331/206
Nhan đề: | Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks |
Tác giả: | Trung Huynh, Hieu Yonggwan Won NTT Institute of Hi-Technology, Nguyen Tat Thanh University, HoChiMinh City, Viet Nam Korea Bio-IT Foundry Center@Gwangju, Chonnam National University, Gwangju 500-757, Republic of Korea |
Từ khoá: | Neural networks Online learning algorithm ELM OS-ELM ReOS-ELM Multiobjective training algorithms |
Năm xuất bản: | 15-thá-2011 |
Trích dẫn: | Pattern Recognition Letters |
Tùng thư/Số báo cáo: | Volume 32, Issue 14;Pages 1930-1935 |
Tóm tắt: | Online learning algorithms have been preferred in many applications due to their ability to learn by the sequentially arriving data. One of the effective algorithms recently proposed for training single hidden- layer feedforward neural networks (SLFNs) is online sequential extreme learning machine (OS-ELM), which can learn data one-by-one or chunk-by-chunk at fixed or varying sizes. It is based on the ideas of extreme learning machine (ELM), in which the input weights and hidden layer biases are randomly chosen and then the output weights are determined by the pseudo-inverse operation. The learning speed of this algorithm is extremely high. However, it is not good to yield generalization models for noisy data and is difficult to initialize parameters in order to avoid singular and ill-posed problems. In this paper, we propose an improvement of OS-ELM based on the bi-objective optimization approach. It tries to minimize the empirical error and obtain small norm of network weight vector. Singular and ill-posed problems can be overcome by using the Tikhonov regularization. This approach is also able to learn data one-by-one or chunk-by-chunk. Experimental results show the better generalization performance of the proposed approach on benchmark datasets. |
Mô tả: | page 6 |
Định danh: | http:/repository-old.ntt.edu.vn/jspui/handle/298300331/206 |
ISSN: | 0167-8655 |
Bộ sưu tập: | GIẢNG VIÊN |
Các tập tin trong tài liệu này:
Tập tin | Mô tả | Kích thước | Định dạng | |
---|---|---|---|---|
RegularizedOnlineSequentialLearningAlgorithmFor.pdf Giới hạn truy cập | 207.31 kB | Adobe PDF | Xem/Tải về Yêu cầu tài liệu |
Khi sử dụng các tài liệu trong Thư viện số phải tuân thủ Luật bản quyền.