Wentao Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Wentao Huang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Haizhang Zhang
School of Mathematics (Zhuhai), Sun Yat-Sen University, Zhuhai 519082, China
1 shared publication Xianghao Jian
China Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd, Guangzhou, China
1 shared publication- Yaqi Zhang
College of Automation, GuangDong Polytechnic Normal University, Guangzhou, China
1 shared publication - Yongxia Han
South China University of Technology
1 shared publication
Latest Publications
- 15 December 2023
- Published by Elsevier in Electric Power Systems Research
- Vol. 228, 110041
Analysis of the calculation methods for shell circulating current and grounding current in 500 kV HGIS and the optimization of grounding scheme
- 15 December 2023
- Published by Elsevier in Electric Power Systems Research
- Vol. 228, 110041
Analysis of the calculation methods for shell circulating current and grounding current in 500 kV HGIS and the optimization of grounding scheme
- 19 October 2023
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
- Vol. 22 (02) , 351-382
Convergence analysis of deep residual networks
Various powerful deep neural network architectures have made great contributions to the exciting successes of deep learning in the past two decades. Among them, deep Residual Networks (ResNets) are of particular importance because they demonstrated great usefulness in computer vision by winning the first place in many deep learning competitions. Also, ResNets are the first class of neural networks in the development history of deep learning that are really deep. It is of mathematical interest and practical meaning to understand the convergence of deep ResNets. We aim at studying the convergence of deep ResNets as the depth tends to infinity in terms of the parameters of the networks. Toward this purpose, we first give a matrix–vector description of general deep neural networks with shortcut connections and formulate an explicit expression for the networks by using the notion of activation matrices. The convergence is then reduced to the convergence of two series involving infinite products of non-square matrices. By studying the two series, we establish a sufficient condition for pointwise convergence of ResNets. We also conduct experiments on benchmark machine learning data to illustrate the potential usefulness of the results.
- 19 October 2023
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
- Vol. 22 (02) , 351-382
Convergence analysis of deep residual networks
Various powerful deep neural network architectures have made great contributions to the exciting successes of deep learning in the past two decades. Among them, deep Residual Networks (ResNets) are of particular importance because they demonstrated great usefulness in computer vision by winning the first place in many deep learning competitions. Also, ResNets are the first class of neural networks in the development history of deep learning that are really deep. It is of mathematical interest and practical meaning to understand the convergence of deep ResNets. We aim at studying the convergence of deep ResNets as the depth tends to infinity in terms of the parameters of the networks. Toward this purpose, we first give a matrix–vector description of general deep neural networks with shortcut connections and formulate an explicit expression for the networks by using the notion of activation matrices. The convergence is then reduced to the convergence of two series involving infinite products of non-square matrices. By studying the two series, we establish a sufficient condition for pointwise convergence of ResNets. We also conduct experiments on benchmark machine learning data to illustrate the potential usefulness of the results.