https://scholars.lib.ntu.edu.tw/handle/123456789/632307
標題: | Heterogeneous recurrent neural networks | 作者: | Lin J.-H.J Chang J.-S TZI-DAR CHIUEH |
關鍵字: | Heterogeneous recurrent neural network; Neural network; Recurrent neural network | 公開日期: | 1998 | 卷: | E81-A | 期: | 3 | 起(迄)頁: | 489-499 | 來源出版物: | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences | 摘要: | Noise cancelation and system identification have been studied for many years, and adaptive filters have proved to be a good means for solving such problems. Some neural networks can be treated as nonlinear adaptive filters, and are thus expected to be more powerful than traditional adaptive filters when dealing with nonlinear system problems. In this paper, two new heterogeneous recurrent neural network (HRNN) architectures will be proposed to identify some nonlinear systems and to extract a fetal electrocardiogram (ECG), which is corrupted by a much larger noise signal, Mother's ECG. The main difference between a heterogeneous recurrent neural network (HRNN) and a recurrent neural network (RNN) is that a complete neural network is used for the feedback path along with an error back-propagation (BP) neural network as the feedforward one. Different feedback neural networks can be used to provide different feedback capabilities. In this paper, a BP neural network is used as the feedback network in the architecture we proposed. And a self-organizing feature mapping (SOFM) network is used next as an alternative feedback network to form another heterogeneous recurrent neural network (HRNN). The heterogeneous recurrent neural networks (HRNN) successfully solve these two problems and prove their superiority to traditional adaptive filters and BP neural networks. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-0032021729&partnerID=40&md5=cf5466d97f3a79fc5d6a8b7297895283 https://scholars.lib.ntu.edu.tw/handle/123456789/632307 |
ISSN: | 9168508 | SDG/關鍵字: | Backpropagation; Computer architecture; Electrocardiography; Error analysis; Feedback; Fetal monitoring; Identification (control systems); Nonlinear control systems; Problem solving; Spurious signal noise; Theorem proving; Heterogeneous recurrent neural networks (HRNN); Self organizing feature mapping (SOFM); Feedforward neural networks |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。