@inproceedings{5f1d13fb82e44f409fd6120e94bb0f4c,
title = "A New Training Algorithm Based on Finite-Time Stable Theory for Neural Networks",
abstract = "A new training algorithm based on finite-time stable theory is presented for neural networks in this paper. A new weight dynamic law is designed, two hyper parameters c1 and β are given out, and a new weight update algorithm is established. To verify performance of our new training algorithm, simulations of the classification problem of images in set CIFAR-10 by using VGG16 are considered. Some typical training algorithms such as SGD-M, AdaGrad, Adam and HJB integrated with them are compared to our algorithm. The simulating results show that our algorithm needs fewer epoches to converge and has superior training performance.",
keywords = "Deep learning, Finite-time stability, Neural networks training algorithm, Nonlinear control",
author = "Mingxing Li and Jianqiang Liang and Yingmin Jia",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 18th Chinese Intelligent Systems Conference, CISC 2022 ; Conference date: 15-10-2022 Through 16-10-2022",
year = "2022",
doi = "10.1007/978-981-19-6226-4\_2",
language = "英语",
isbn = "9789811962257",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "9--17",
editor = "Yingmin Jia and Weicun Zhang and Yongling Fu and Shoujun Zhao",
booktitle = "Proceedings of 2022 Chinese Intelligent Systems Conference - Volume II",
address = "德国",
}