Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks

doi:10.1109/TNNLS.2012.2200695

淡江大學機構典藏 > 工學院 > 水資源及環境工程學系暨研究所 > 期刊論文 > Item 987654321/80119

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

文件中的档案:

档案	描述	大小	格式	浏览次数
06218199.pdf		606Kb	Adobe PDF	1	检视/开启
index.html		0Kb	HTML	291	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....