基于CappedL1罚函数的组稀疏模型 下载积分: 5000 内容提示: 研究与开发现代计算机 2018.11 中文章编号:1007-1423 (2018)32-0022-04 DOI:10.3969/j.issn.1007-1423.2018.32.006基于 Capped L1 罚函数的组稀疏模型崔立鹏,于玲,范平平,吴宝杰,翟永君(天津轻工职业技术学院电子信息与自动化学院,天津 300350)摘要:近年...
基于capped-l1范数的提高TWSVM算法鲁棒性的方法本发明涉及数据处理领域,公开了一种基于cappedl1范数的提高TWSVM算法鲁棒性的方法,包括:输入原始数据矩阵M和参数C业巧林王春燕
近年来,稀疏优化广泛应用于机器学习,统计回归和计算视觉等领域当中,稀疏优化问题的研究愈发重要.本文针对多元线性回归中回归系数的估计问题,基于Huber损失的鲁棒性和折叠凹罚的无偏性,考虑了基于Huber损失和线性不等式约束的稀疏优化模型.首先,本文给出了稀疏优化的原问题,基于Capped-L1正则的松弛问题和基于约束惩罚的无约...
The capped L1-norm with upper bound value is used to construct the optimization problem instead of L2-norm, which weakens the influence of outliers and noise points on the construction of two hyperplanes to a certain extent and enhances the robustness of the model. In addition, a simple and ...
FRTELM first replaced the inequality constraints in TELM with equality constraints, and then introduced the cappedL1-norm distance metric to replace theL2-norm distance metric in TELM. FRTELM not only retains the advantages of TELM, but also overcomes the shortcomings of TELM exaggeration of ...
Capped-L1正则方向稳定点光滑化惩罚算法对多元线性回归中回归系数的估计问题,本文考虑了基于Huber损失和线性不等式约束的稀疏优化模型.首先,给出了稀疏优化的原问题,基于Capped-L1正则的松弛问题和基于约束惩罚的无约束问题三种模型.其次,借助惩罚模型方向稳定点的下界性质,在一定条件下分析了三种模型全局最优解的等价性....
Capped L1-normVGGnetCIFARConvolutional neural networkFLOPsThe blistering progress of convolutional neural networks (CNNs) in numerous applications of the real-world usually obstruct by a surge in network volume and computational cost. Recently, researchers concentrate on eliminating these issues by ...
对多元线性回归中回归系数的估计问题,本文考虑了基于Huber损失和线性不等式约束的稀疏优化模型.首先,给出了稀疏优化的原问题,基于Capped-L1正则的松弛问题和基于约束惩罚的无约束问题三种模型.其次,借助惩罚模型方向稳定点的下界性质,在一定条件下分析了三种模型全局最优解的等价性.最后,提出了光滑化惩罚算法,并证明了该...
To handle this problem, in this paper, we propose a novel Robust Capped L1-norm Twin Support Vector Machine with Privileged Information (R-CTSVM+). The proposed pair of regularization functions (up- and down-bound) can definitely help to increase the learning model's tolerance to disturbance,...
Capped L1-normVGGnetCIFARConvolutional neural networkFLOPsThe blistering progress of convolutional neural networks (CNNs) in numerous applications of the real-world usually obstruct by a surge in network volume and computational cost. Recently, researchers concentrate on eliminating these issues by ...