引用本文:韩敏,史志伟,席剑辉.应用递归神经网络学习周期运动吸引子轨迹[J].控制理论与应用,2006,23(4):497~502.[点击复制]
HAN Min, SHI Zhi-wei, XI Jian-hui.Learning the trajectories of periodic attractor using recurrent neural network[J].Control Theory and Technology,2006,23(4):497~502.[点击复制]
应用递归神经网络学习周期运动吸引子轨迹
Learning the trajectories of periodic attractor using recurrent neural network
摘要点击 1636  全文点击 1473  投稿时间:2004-07-02  修订日期:2005-10-25
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  
  2006,23(4):497-502
中文关键词  递归神经网络  周期吸引子  泛化能力
英文关键词  recurrent neural network  periodic attractor  generalization ability
基金项目  国家自然科学基金资助项目(60374064).
作者单位
韩敏,史志伟,席剑辉 大连理工大学 电子与信息工程学院,辽宁 大连116023
沈阳航空工业学院 自动化系,辽宁 沈阳110034 
中文摘要
      采用递归神经网络学习非线性周期运动的吸引子轨迹.网络的拓扑结构基于非线性系统的状态空间表达式,网络权值通过时序反向传播算法调整.探讨了不同样本轨迹和网络结构对递归神经网络预测性能的影响.神经网络的性能评估建立在多条测试样本轨迹的基础上,可以更为客观地评价递归神经网络预测性能.对van der Pol方程的仿真结果表明:网络的泛化能力对训练样本轨迹的依赖性较强,从不同训练轨迹上得到的递归神经网络性能差异较大;需要选择合适的递归神经网络结构参数以提高神经网络的泛化能力.
英文摘要
      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.