文献类型：期刊文献

英文题名：Robustly Fitting and Forecasting Dynamical Data With Electromagnetically Coupled Artificial Neural Network: A Data Compression Method

作者：Wang, Ziyin[1];Liu, Mandan[1];Cheng, Yicheng[2];Wang, Rubin[3]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Purdue Univ, Dept Comp Sci, W Lafayette, IN 46202 USA;[3]East China Univ Sci & Technol, Inst Cognit Neurodynam, Shanghai 200237, Peoples R China

年份：2017

卷号：28

期号：6

起止页码：1397

外文期刊名：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录：;EI(收录号：20161502223394);WOS:【SCI-EXPANDED(收录号:WOS:000401982100012)】；

基金：This work was supported in part by the Fundamental Research Funds for the Central Universities of China under Grant WH1213010, in part by the Fundamental Research Funds for the Central Universities of China within the Ministry of Education Doctoral Foundation under Grant 20120074110020, and in part by the National Natural Science Foundation of China under Grant 11232005 and Grant 11472104. (Corresponding author: Mandan Liu.)

语种：英文

外文关键词：Artificial neural network (ANN); data compression; dynamic data fitting; electromagnetic coupling

摘要：In this paper, a dynamical recurrent artificial neural network (ANN) is proposed and studied. Inspired from a recent research in neuroscience, we introduced nonsynaptic coupling to form a dynamical component of the network. We mathematically proved that, with adequate neurons provided, this dynamical ANN model is capable of approximating any continuous dynamic system with an arbitrarily small error in a limited time interval. Its extreme concise Jacobian matrix makes the local stability easy to control. We designed this ANN for fitting and forecasting dynamic data and obtained satisfied results in simulation. The fitting performance is also compared with those of both the classic dynamic ANN and the state-of-the-art models. Sufficient trials and the statistical results indicated that our model is superior to those have been compared. Moreover, we proposed a robust approximation problem, which asking the ANN to approximate a cluster of input-output data pairs in large ranges and to forecast the output of the system under previously unseen input. Our model and learning scheme proposed in this paper have successfully solved this problem, and through this, the approximation becomes much more robust and adaptive to noise, perturbation, and low-order harmonic wave. This approach is actually an efficient method for compressing massive external data of a dynamic system into the weight of the ANN.