首页|基于光滑化L1正则项的随机配置网络

基于光滑化L1正则项的随机配置网络

扫码查看
原文链接
  • 万方数据
  • 维普
为了提高随机配置网络(stochastic configuration networks，SCN)的泛化能力，提出一种适用于SCN的光滑化L1正则化方法。针对L1正则化算子局部不可微的缺陷，在曲线不光滑点的邻域内进行光滑处理，并在此基础上构建SCN的光滑误差函数，提出增量计算权值的算法，进而以交替方向乘子法为基础给出权值的全局优化算法，并且在理论上分析算法的收敛性。与L1正则化的稀疏性和L2正则化均匀减小参数的特点相比，所提出方法按重要程度保留数据的全部特征，使参数既保持在较小的范围内又具有层次分明的分布，从而使网络具有更好的泛化能力。最后，通过数值仿真实验验证了所提出方法的可行性和有效性。
Smoothing L1 regularization for stochastic configuration networks
In order to improve the generalization capability of stochastic configuration networks(SCNs),a smooth L1 regularization method for SCNs is proposed.Aiming at the defect of local non-differentiability of the L1 regularization operator,smoothing is carried out in the neighborhood of non-smooth points of the curve.The convex error function of the SCN is constructed on this basis,and an algorithm for incremental calculation of the weights of the SCN is proposed.Furthermore,the global optimization algorithm is proposed based on the alternating direction multiplier method,and the convergence of the algorithm is analyzed theoretically.Compared with the sparsity of L1 regularization and the uniform reduction of parameters by L2 regularization,the proposed method retains all features of the data according to the degree of importance,the parameters are not only kept in a small range,but also have hierarchical distribution,so that the network has better generalization ability.Finally,the feasibility and effectiveness of the proposed method are verified by some numerical simulations.

smoothing regularizationstochastic configuration networksgeneralization capabilityalternating direction multiplier methodconvergence analysisdata feature

刘晶晶、刘业峰、马祎航、富月

展开 >

沈阳工学院基础课部,辽宁沈抚示范区 113122

沈阳工学院辽宁省数控机床信息物理融合与智能制造重点实验室,辽宁沈抚示范区 113122

沈阳工学院机械工程与自动化学院,辽宁沈抚示范区 113122

东北大学流程工业综合自动化国家重点实验室,沈阳 110819

展开 >

光滑正则化 随机配置网络 泛化能力 交替方向乘子法 收敛性分析 数据特征

国家自然科学基金辽宁省自然科学基金重点领域联合开放基金辽宁省自然科学基金重点领域联合开放基金辽宁省自然科学基金重点领域联合开放基金沈抚示范区本级科技计划沈抚示范区本级科技计划沈阳工学院青年骨干教师科研基金

620732262022-KF-11-012020-KF-11-092021-KF-11-052020JH132021JH07QN202210

2024

10.13195/j.kzyjc.2022.1612

控制与决策
东北大学

控制与决策

CSTPCD北大核心
影响因子：1.227
ISSN：1001-0920
年,卷(期)：2024.39(3)
  • 25