云南高校图书馆联盟文献共享服务平台- REGULARIZATION

REGULARIZATION: 作品数：453被引量：714H指数：12; 导出分析报告; 相关领域：理学更多>>; 相关作者：王海贤戴前伟董莉张涛陈黎霞更多>>; 相关机构：东南大学上海交通大学中南大学物理与信息科学学院更多>>; 相关期刊：更多>>; 相关基金：国家自然科学基金国家重点基础研究发展计划中国博士后科学基金国家教育部博士点基金更多>>

A regularization method for delivering the fourth-order derivative of experimental data and its applications in fluid-structure interactions: 《Science China(Technological Sciences)》2025年第3期359-376,共18页Fan DUAN Jin-Jun WANG; supported by the National Natural Science Foundation of China(Grant Nos.12127802 and 11721202)。; In the experimental investigation of fluid-structure interactions regarding the undulatory motion like flag flapping or fish swimming,solving the force distribution on the flexible body stands as an indispensable ende...; 关键词：high-order numerical derivative REGULARIZATION FILM fluid-structure interactions bending force

Fractal autoencoder with redundancy regularization for unsupervised feature selection: 《Science China(Information Sciences)》2025年第2期85-98,共14页Meiting SUN Fangyu LI Honggui HAN; supported by National Key Research and Development Project(Grant Nos.2022YFB3305800-5,2023YFB3307300);National Natural Science Foundation of China(Grant Nos.62125301,62373014,92267107);Beijing Youth Scholar(Grant No.037)。; Feature selection is a crucial step in data preprocessing because feature selection reduces the dimensionality of data by eliminating irrelevant and redundant features.Since manual labeling is expensive,unsupervised f...; 关键词：unsupervised feature selection fractal autoencoder correspondence neural network selection neural network re-dundancy regularization strategy

Box-Constrained Nonlinear Weighted Anisotropic TV Regularization for Beam Hardening Artifacts Reduction in CT: 《Journal of Applied Mathematics and Physics》2025年第2期392-399,共8页Xue Shi; In Computed Tomography (CT), the beam hardening artifacts are caused by polychromatic X-ray beams applied in real medical imaging. In this article, we applied the recently proposed box-constrained nonlinear weighted a...; 关键词：Beam Hardening Artifacts Box-Constrained NWATV Computed Tomography

Markov Chain Monte Carlo-Based L1/L2 Regularization and Its Applications in Low-Dose CT Denoising: 《Journal of Applied Mathematics and Physics》2025年第2期419-428,共10页Shuoqi Yu; In this paper, a low-dose CT denoising method based on L1/L2regularization method of Markov chain Monte Carlo is studied. Firstly, the mathematical model and regularization method of low-dose CT denoising are summariz...; 关键词：Low-Dose CT Denoising REGULARIZATION Statistical Inverse Problem MCMC Sampling

SensFL:Privacy-Preserving Vertical Federated Learning with Sensitive Regularization: 《Computer Modeling in Engineering & Sciences》2025年第1期385-404,共20页Chongzhen Zhang Zhichen Liu Xiangrui Xu Fuqiang Hu Jiao Dai Baigen Cai Wei Wang; supported by Systematic Major Project of Shuohuang Railway Development Co.,Ltd.,National Energy Group(Grant Number:SHTL-23-31);Beijing Natural Science Foundation(U22B2027).; In the realm of Intelligent Railway Transportation Systems,effective multi-party collaboration is crucial due to concerns over privacy and data silos.Vertical Federated Learning(VFL)has emerged as a promising approach...; 关键词：Vertical federated learning PRIVACY DEFENSES

ADAPTIVE REGULARIZED QUASI-NEWTON METHOD USING INEXACT FIRST-ORDER INFORMATION: 《Journal of Computational Mathematics》2024年第6期1656-1687,共32页Hongzheng Ruan Weihong Yang; supported by the National Natural Science Foundation of China(Grant No.NSFC-11971118).; Classical quasi-Newton methods are widely used to solve nonlinear problems in which the first-order information is exact.In some practical problems,we can only obtain approximate values of the objective function and i...; 关键词：Inexact first-order information REGULARIZATION Quasi-Newton method

A General Framework for Nonconvex Sparse Mean-CVaR Portfolio Optimization Via ADMM: 《Journal of the Operations Research Society of China》2024年第4期1022-1047,共26页Ke-Xin Sun Zhong-Ming Wu Neng Wan; supported by the National Natural Science Foundation of China(No.12001286);the Project funded by China Postdoctoral Science Foundation(No.2022M711672).; This paper presents a general framework for addressing sparse portfolio optimization problems using the mean-CVaR(Conditional Value-at-Risk)model and regularization techniques.The framework incorporates a non-negative...; 关键词：Portfolio optimization Mean-CVaR Sparse regularization Alternating direction method of multipliers

Two-Stage Approach for Targeted Knowledge Transfer in Self-Knowledge Distillation: 《IEEE/CAA Journal of Automatica Sinica》2024年第11期2270-2283,共14页Zimo Yin Jian Pu Yijie Zhou Xiangyang Xue; supported by the National Natural Science Foundation of China (62176061)。; Knowledge distillation(KD) enhances student network generalization by transferring dark knowledge from a complex teacher network. To optimize computational expenditure and memory utilization, self-knowledge distillati...; 关键词：Cluster-based regularization iterative prediction refinement model-agnostic framework self-knowledge distillation(SKD) two-stage knowledge transfer

Combining Innovative CVTNet and Regularization Loss for Robust Adversarial Defense: 《Journal of Computer Science & Technology》2024年第5期1078-1093,共16页Wei-Dong Wang Zhi Li Li Zhang; supported by the National Natural Science Foundation of China under Grant No.62062023.; Deep neural networks(DNNs)are vulnerable to elaborately crafted and imperceptible adversarial perturbations.With the continuous development of adversarial attack methods,existing defense algorithms can no longer defen...; 关键词：deep learning adversarial defense vision transformer image reconstruction

Experimental Data-Driven Flow Field Prediction for Compressor Cascade based on Deep Learning and l_(1)Regularization: 《Journal of Thermal Science》2024年第5期1867-1882,共16页LIU Tantao GAO Limin LI Ruiyu; the support of the National Natural Science Foundation of China(No.52106053,No.92152301)。; For complex flows in compressors containing flow separations and adverse pressure gradients,the numerical simulation results based on Reynolds-averaged Navier-Stokes(RANS)models often deviate from experimental measure...; 关键词：experimental data-driven compressor cascade deep learning l_(1)regularization

REGULARIZATION