Reinforced two-step-ahead weight adjustment technique for online training of recurrent neural networks.
IEEE Trans. Neural Netw. Learning Syst.（2012）
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.
更多查看译文
关键词
rnn,2sa,two-step-ahead forecasts,real-time recurrent learning algorithm,streamflow forecast,time-lag effects,learning (artificial intelligence),time series forecast,rtrl,flood forecasts,recurrent neural network (rnn),online recurrent neural networks training,recurrent neural nets,real-time recurrent learning (rtrl) algorithm,reinforced two-step-ahead weight adjustment technique,time series,time series analysis,vectors,recurrent neural networks,learning artificial intelligence,predictive models
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要