| 引用本文: | 褚菲,苏嘉铭,梁涛,陈俊龙,王雪松,马小平.基于lasso和elastic net的宽度学习系统网络结构稀疏方法[J].控制理论与应用,2020,37(12):2543~2550.[点击复制] |
| CHU Fei,SU Jia-ming,LIANG Tao,CHEN Jun-long,WANG Xue-song,MA Xiao-ping.Sparsity method for network structure of broad learning system based on lasso and elastic net[J].Control Theory and Technology,2020,37(12):2543~2550.[点击复制] |
|
| 基于lasso和elastic net的宽度学习系统网络结构稀疏方法 |
| Sparsity method for network structure of broad learning system based on lasso and elastic net |
| 摘要点击 2405 全文点击 826 投稿时间：2020-03-31 修订日期：2020-08-19 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2020.00178 |
| 2020,37(12):2543-2550 |
| 中文关键词 宽度学习系统 网络结构 lasso elastic net |
| 英文关键词 broad learning system network structure lasso elastic net |
| 基金项目 国家自然科学基金项目(61973304, 61503384, 61702195, 61751202), 国家重点研发项目(2019YFA0706200, 2019YFB1703600), 江苏省六大人才 高峰项目(DZXX–045), 江苏省科技计划项目(BK20191339), 广州市科技重大专项项目(202007030006), 徐州市科技创新计划项目(KC19055), 矿 冶过程自动控制技术国家重点实验室开放课题项目(BGRIMM–KZSKL–2019–10)资助. |
|
| 中文摘要 |
| 本文提出了一种基于lasso和elastic net的宽度学习系统(BLS)网络结构稀疏方法, 将标准BLS目标函数中的
L2范数分别替换为lasso和elastic net, 利用这两种正则化技术来约束网络输出权重, 衡量每个网络节点输出权重对
预测的影响程度, 将多余的节点进行剔除, 提高了网络结构的稀疏性. 通过对一些回归数据集进行实验, 可以看到
本文提出的方法在不损失预测精度的前提下, 同时简化了网络结构. |
| 英文摘要 |
| This paper proposes a sparsity method for network structure of broad learning system (BLS) based on lasso
and elastic net. The L2-norm in the standard BLS objective function is replaced by the lasso and the elastic net respectively.
These two regularization techniques are used to constrain the output weight of each network node, so as to measure the
impact of each node’s output weight on the prediction. In this way, the redundant nodes are eliminated and the sparsity
of network structure is improved. Through the experiments on some regression datasets, it can be seen that the proposed
method can simplify the network structure without losing the prediction accuracy. |
|
|
|
|
|