Zobrazeno 1 - 10
of 1 160
pro vyhledávání: '"HUANG Jianguo"'
Autor:
Li Hao, Gong Qinghua, Yuan Shaoxiong, Wang Jun, Huang Zhihao, Cheng Yuesong, Chen Jingye, Huang Jianguo
Publikováno v:
Redai dili, Vol 43, Iss 3, Pp 408-416 (2023)
With the advancement of urbanization in China, hilly and gently sloping mountainous areas have become areas of high disturbance owing to urban construction, with the disturbed areas also having a high incidence of mountain disasters. The large hilly
Externí odkaz:
https://doaj.org/article/2c178b9da1284eef8106744bb1635250
Autor:
Huang, Jianguo, Xu, Yuejin
In this paper, for solving a class of linear parabolic equations in rectangular domains, we have proposed an efficient Parareal exponential integrator finite element method. The proposed method first uses the finite element approximation with continu
Externí odkaz:
http://arxiv.org/abs/2412.01138
Autor:
Huang, Jianguo, Xu, Yuejin
In this paper, in order to improve the spatial accuracy, the exponential integrator Fourier Galerkin method (EIFG) is proposed for solving semilinear parabolic equations in rectangular domains. In this proposed method, the spatial discretization is f
Externí odkaz:
http://arxiv.org/abs/2411.19265
This paper aims to devise an adaptive neural network basis method for numerically solving a second-order semilinear partial differential equation (PDE) with low-regular solutions in two/three dimensions. The method is obtained by combining basis func
Externí odkaz:
http://arxiv.org/abs/2411.01998
Conformal prediction, as an emerging uncertainty quantification technique, typically functions as post-hoc processing for the outputs of trained classifiers. To optimize the classifier for maximum predictive efficiency, Conformal Training rectifies t
Externí odkaz:
http://arxiv.org/abs/2410.09408
The rapid development of Large Language Models (LLMs) in vertical domains, including intellectual property (IP), lacks a specific evaluation benchmark for assessing their understanding, application, and reasoning abilities. To fill this gap, we intro
Externí odkaz:
http://arxiv.org/abs/2406.12386
Graph Neural Networks have achieved remarkable accuracy in semi-supervised node classification tasks. However, these results lack reliable uncertainty estimates. Conformal prediction methods provide a theoretical guarantee for node classification tas
Externí odkaz:
http://arxiv.org/abs/2405.14303
Autor:
Wei, Hongxin, Huang, Jianguo
TorchCP is a Python toolbox for conformal prediction research on deep learning models. It contains various implementations for posthoc and training methods for classification and regression tasks (including multi-dimension output). TorchCP is built o
Externí odkaz:
http://arxiv.org/abs/2402.12683
Conformal prediction, as an emerging uncertainty qualification technique, constructs prediction sets that are guaranteed to contain the true label with pre-defined probability. Previous works often employ temperature scaling to calibrate the classifi
Externí odkaz:
http://arxiv.org/abs/2402.04344
Autor:
Huang, Jianguo, Qiu, Yue
Neural operators (NO) are discretization invariant deep learning methods with functional output and can approximate any continuous operator. NO have demonstrated the superiority of solving partial differential equations (PDEs) over other deep learnin
Externí odkaz:
http://arxiv.org/abs/2402.00825