Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks
學年 101
學期 1
出版（發表）日期 2012-08-01
作品名稱 Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks
作品名稱（其他語言）
著者 Chang, Li-Chiu; Chen, Pin-An; Chang, Fi-John
單位 淡江大學水資源及環境工程學系
出版者 Piscataway: Institute of Electrical and Electronics Engineers
著錄名稱、卷期、頁數 IEEE Transactions on Neural Networks and Learning Systems 23(8), pp.1269-1278
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.
關鍵字 Real-time recurrent learning (RTRL) algorithm, recurrent neural network (RNN);streamflow forecast;time series forecast
語言 en_US
ISSN 2162-2388
期刊性質 國外
收錄於 SCI EI
產學合作
通訊作者
審稿制度 是
國別 USA
公開徵稿
出版型式 ,電子版,紙本
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/80119 )

機構典藏連結