In this paper, we present a deep neural network based adaptive learning (DNN-AL) approach for switched systems. Currently, deep neural network based methods are actively developed for learning governing equations in unknown dynamic systems, but their efficiency can degenerate for switching systems, where structural changes exist at discrete time instants. In this new DNN-AL strategy, observed datasets are adaptively decomposed into subsets, such that no structural changes within each subset. During the adaptive procedures, DNNs are hierarchically constructed, and unknown switching time instants are gradually identified. Especially, network parameters at previous iteration steps are reused to initialize networks for the later iteration steps, which gives efficient training procedures for the DNNs. For the DNNs obtained through our DNN-AL, bounds of the prediction error are established. Numerical studies are conducted to demonstrate the efficiency of DNN-AL.
翻译:在本文中,我们展示了一种基于深神经网络的转换系统适应性学习(DNN-AL)的深神经网络方法。目前,正在积极开发深神经网络方法,以学习未知动态系统中的方程式,但对于在离散时间瞬间存在结构变化的切换系统而言,其效率可能会下降。在这个新的DNN-AL战略中,观测到的数据集在适应性地分解成子集,因此每个子集没有结构变化。在适应性程序期间,DNN是按等级构建的,并逐渐确定未知的切换时间。特别是,以前迭代步骤中的网络参数被重新用于初始化网络,用于以后的迭代步骤,为DNNS提供有效的培训程序。对于通过我们的DNN-AL获得的DNN,则确定了预测错误的界限。进行了数值研究,以证明DNN-AL的效率。