Tao Zhang

Dr. Tao Zhang


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 December 2024 in Neurocomputing
Verified
Journal Article
Closed access
TZTao Zhang
Tao Zhang
QTQing Tao
Qing Tao
LYLinjun Yu
Linjun Yu
HYHaohao Yi
Haohao Yi
JCJiawei Chen
Jiawei Chen

1 May 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
TZTao Zhang
Tao Zhang
QZQingyan Zhou
Qingyan Zhou
YZYue Zheng
Yue Zheng
HYHuiwen Yu
Huiwen Yu

1 January 2021 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
FCFang Chen
Fang Chen
TZTao Zhang
Tao Zhang
RLRuilin Liu
Ruilin Liu
Active learning is aimed to sample the most informative data from the unlabeled pool, and diverse clustering methods have been applied to it. However, the distance‐based clustering methods usually cannot perform well in high dimensions and even begin to fail. In this paper, we propose a new active learning method combined with variational autoencoder (VAE) and density‐based spatial clustering of applications with noise (DBSCAN). It overcomes the difficulty of distance representation in high dimensions and prevents the distance concentration phenomenon from occurring in the computational learning literature with respect to high‐dimensional p‐norms. Finally, we compare our method with four common active learning methods and two other clustering algorithms combined with VAE on three datasets. The results demonstrate that our approach achieves competitive performance, and it is a new batch mode active learning algorithm designed for neural networks with a relatively small query batch size.

21 November 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
TZTao Zhang
Tao Zhang
HYHaohao Yi
Haohao Yi
ZTZhen Tai
Zhen Tai
JZJian Zou
Jian Zou
YZYue Zheng
Yue Zheng

22 March 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
TZTao Zhang
Tao Zhang
XZXinran Zhu
Xinran Zhu
In scientific and engineering calculation, the effective solution of partial differential equations (PDEs) has great significance. This paper presents an innovative method based on the combination of a U-Net neural network with Fourier neural operators, aiming to improve the accuracy and efficiency of solving partial differential equations. U-Net neural networks with a unique encoding–decoder structure and hopping connections can efficiently extract and integrate spatial-domain features and accurately describe the spatial structure of PDEs. The Fourier neural operator combines the advantages of neural networks and Fourier transform to learn the mapping relationship of high-dimensional data by training the linear transformation parameters in the detailed frequency domain of the data. Fourier transform is used to explore and process the frequency-domain features and capture the frequency characteristics of the solution of partial differential equations. By combining the two, this method not only retains spatial details but also makes full use of frequency-domain information, which significantly reduces the dependence of the model on large-scale data and improves the generalization ability of the model. The experimental results show that compared with the traditional method, this method performs well in various complex partial differential equation (PDE) solving tasks and achieves high accuracy.

25 February 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
TZTao Zhang
Tao Zhang
欣朱欣然 朱
欣然 朱
In scientific and engineering computations, the efficient solution of partial differential equations (PDEs) is of great significance. This paper proposes an innovative method based on the combination of the U-Net neural network and the Fourier neural operator, aiming to improve the accuracy and efficiency of solving PDEs. The unique encoder-decoder structure and skip connections of the U-Net neural network can effectively extract and integrate spatial domain features, accurately depicting the spatial structure of PDEs. The Fourier neural operator, by means of the Fourier transform, deeply explores and processes features in the frequency domain, capturing the frequency characteristics of the solutions of PDEs. By organically combining the two, this method not only preserves spatial details but also makes full use of frequency domain information. It significantly reduces the model's dependence on large scale data and enhances its generalization ability. Experimental results show that compared with traditional methods, this method performs outstandingly in various complex partial differential equation(PDE) solving tasks, achieving higher accuracy. It provides a new and highly promising solution for the solution of PDEs and is expected to be widely applied in related fields.