%0 Journal Article
%T Learning the trajectories of periodic attractor using recurrent neural network<br>应用递归神经网络学习周期运动吸引子轨迹
%A HAN Min
%A SHI Zhi-wei
%A XI Jian-hui
%A <br>韩敏
%A 史志伟
%A 席剑辉
%J 控制理论与应用
%D 2006
%I 
%X A kind of RNN(recurrent neural network) is applied to the learning of periodic attractor trajectories for nonlinear system. The network topology is based on the state-space representation, and the network parameters are optimized by the back-propagation through time algorithm. Investigations are then conducted into the model performance influenced by different training trajectories and different structure parameters. The model evaluation rule is based on multi-trajectory, which makes the investigation more objective. Simulation results from the van der Pol system show that the generalization ability is dependent on the training trajectory, different trajectories result in a significant different prediction performance; Simulation results also show that the structure parameters of the neural network should be carefully chosen so that better generalization ability can be obtained.
%K recurrent neural network
%K periodic attractor
%K generalization ability<br>递归神经网络
%K 周期吸引子
%K 泛化能力
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=970898A57DFC021F93AB51667BAED7F7&aid=47658316D7D1A359&yid=37904DC365DD7266&vid=EA389574707BDED3&iid=E158A972A605785F&sid=CEFA535D01173730&eid=51F9E747BA1ACB45&journal_id=1000-8152&journal_name=控制理论与应用&referenced_num=0&reference_num=13