Výsledky vyhledávání - "Huang, Shengjun"

Report

Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons

Autor: Ding, Binbin, Yang, Penghui, Ge, Zeqing, Huang, Shengjun

Federated learning enables multiple clients to collaboratively train machine learning models under the overall planning of the server while adhering to privacy requirements. However, the server cannot directly oversee the local training process, crea

Externí odkaz: http://arxiv.org/abs/2408.08655

Zobrazit plný text záznamu

Report

Inversion-DeepONet: A Novel DeepONet-Based Network with Encoder-Decoder for Full Waveform Inversion

Autor: Guo, Zekai, Chai, Lihui, Huang, Shengjun, Li, Ye

Full waveform inversion (FWI) plays a crucial role in the field of geophysics. There has been lots of research about applying deep learning (DL) methods to FWI. The success of DL-FWI relies significantly on the quantity and diversity of the datasets.

Externí odkaz: http://arxiv.org/abs/2408.08005

Zobrazit plný text záznamu

Report

VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equations

Autor: Shan, Bin, Li, Ye, Huang, Shengjun

Although physics-informed neural networks(PINNs) have progressed a lot in many real applications recently, there remains problems to be further studied, such as achieving more accurate results, taking less training time, and quantifying the uncertain

Externí odkaz: http://arxiv.org/abs/2211.16753

Zobrazit plný text záznamu

Report

A Survey of Learning on Small Data: Generalization, Optimization, and Challenge

Autor: Cao, Xiaofeng, Bu, Weixin, Huang, Shengjun, Zhang, Minling, Tsang, Ivor W., Ong, Yew Soon, Kwok, James T.

Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of A

Externí odkaz: http://arxiv.org/abs/2207.14443

Zobrazit plný text záznamu

Report

Large-scale matrix optimization based multi microgrid topology design with a constrained differential evolution algorithm

Autor: Li, Wenhua, Huang, Shengjun, Zhang, Tao, Wang, Rui, Wang, Ling

Binary matrix optimization commonly arise in the real world, e.g., multi-microgrid network structure design problem (MGNSDP), which is to minimize the total length of the power supply line under certain constraints. Finding the global optimal solutio

Externí odkaz: http://arxiv.org/abs/2207.08327

Zobrazit plný text záznamu

Akademický článek

Nodal Invulnerability Recovery Considering Power Generation Balance: A Bi-Objective Robust Optimization Framework.

Autor: Zhang, Xueyang¹ (AUTHOR) huangshengjun@nudt.edu.cn, Huang, Shengjun¹ (AUTHOR), Li, Qingxia¹ (AUTHOR), Wang, Rui¹ (AUTHOR), Zhang, Tao¹ (AUTHOR), Guo, Bo¹ (AUTHOR)

Publikováno v: Mathematics (2227-7390). Jun2024, Vol. 12 Issue 12, p1791. 19p.