@inproceedings{1dfb1e1760684c7b8777717676705839,
title = "Univariate relu neural network and its application in nonlinear system identification",
abstract = "ReLU (rectified linear units) neural network has received significant attention since its emergence. In this paper, a univariate ReLU (UReLU) neural network is proposed to both model the nonlinear dynamic system and reveal the insights about the system. Specifically, the neural network consists of neurons with linear and UReLU activation functions, and the UReLU functions are defined as the ReLU functions respect to each dimension. The UReLU neural network is a single hidden layer neural network, and the structure is relatively simple. The initialization of the neural network employs the decoupling method, which provides a good initialization and some insight into the nonlinear system. Compared with normal ReLU neural network, the number of parameters of UReLU network is less, but it still provide a good approximation of the nonlinear dynamic system. The performance of the UReLU neural network is shown through a Hysteretic benchmark system: the BoucWen system. Simulation results verify the effectiveness of the proposed method.",
keywords = "Decoupling method, Identification, Neural network, Univariate ReLU function",
author = "Xinglong Liang and Jun Xu",
note = "Publisher Copyright: {\textcopyright} The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.; Chinese Intelligent Systems Conference, CISC 2020 ; Conference date: 24-10-2020 Through 25-10-2020",
year = "2021",
doi = "10.1007/978-981-15-8450-3\_71",
language = "英语",
isbn = "9789811584497",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "679--687",
editor = "Yingmin Jia and Weicun Zhang and Yongling Fu",
booktitle = "Proceedings of 2020 Chinese Intelligent Systems Conference - Volume I",
address = "德国",
}