.png){kind=icon}
返回
Neural network input feature selection using structured l2 - norm penalization
.png){kind=icon}
OA
AI
DOI：10.1007/s10489-022-03539-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Artificial neural networks are referred to as universal approximators due to their inherent ability to reconstruct complex linear and nonlinear output maps conceived as input-output relationships from data sets. This can be done by reducing large networks via regularization in order to establish compact models containing fewer parameters aimed at describing vital dependencies in data sets. In situations where the data sets contain non-informative input features, devising a continuous, optimal input feature selection technique can lead to improved prediction or classification. We propose a continuous input selection technique through a dimensional reduction mechanism using a 'structured' l(2) - norm regularization. The implementation is done by identifying the most informative feature subsets from a given data set via an adaptive training mechanism. The adaptation involves introducing a novel, modified gradient approach during training to deal with the non-differentiability associated with the gradient of the structured norm penalty. When the method is applied to process data sets, results indicate that the most informative inputs of artificial neural networks can be selected using a structured l(2) - norm penalization.
Keyword:
Input optimization
Sparsity
Regularization
Structured penalty
Feature selection
Deep learning
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Cytotoxicity and biological effects of functional nanomaterials delivered to various cell lines
PREAI
分享收藏
A survey on swarm intelligence approaches to feature selection in data mining数据挖掘中特征选择的群体智能方法综述
PREAI
分享收藏Ensemble feature selection in medical datasets: Combining filter, wrapper, and embedded feature selection results医学数据集中的集成特征选择: 结合过滤器，包装器和嵌入式特征选择结果.png)
EXPERT SYSTEMS
EXPERT SYSTEMSIF2.3
PREAI
分享收藏Hypergraph based multi-task feature selection for multimodal classification of Alzheimer's disease基于超图的多任务特征选择在阿尔茨海默病多模态分类中的应用
PREAI
分享收藏
查看更多内容