English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 57615/91160 (63%)
造访人次 : 13556737      在线人数 : 297
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻

    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/80119

    题名: Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks
    作者: Chang, Li-Chiu;Chen, Pin-An;Chang, Fi-John
    贡献者: 淡江大學水資源及環境工程學系
    关键词: Real-time recurrent learning (RTRL) algorithm, recurrent neural network (RNN);streamflow forecast;time series forecast
    日期: 2012-08-01
    上传时间: 2013-01-18 00:04:08 (UTC+8)
    出版者: Piscataway: Institute of Electrical and Electronics Engineers
    摘要: A reliable forecast of future events possesses great value. The main purpose of this paper is to propose an innovative learning technique for reinforcing the accuracy of two-step-ahead (2SA) forecasts. The real-time recurrent learning (RTRL) algorithm for recurrent neural networks (RNNs) can effectively model the dynamics of complex processes and has been used successfully in one-step-ahead forecasts for various time series. A reinforced RTRL algorithm for 2SA forecasts using RNNs is proposed in this paper, and its performance is investigated by two famous benchmark time series and a streamflow during flood events in Taiwan. Results demonstrate that the proposed reinforced 2SA RTRL algorithm for RNNs can adequately forecast the benchmark (theoretical) time series, significantly improve the accuracy of flood forecasts, and effectively reduce time-lag effects.
    關聯: IEEE Transactions on Neural Networks and Learning Systems 23(8), pp.1269-1278
    DOI: 10.1109/TNNLS.2012.2200695
    显示于类别:[水資源及環境工程學系暨研究所] 期刊論文


    档案 描述 大小格式浏览次数
    06218199.pdf606KbAdobe PDF0检视/开启



    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回馈