Cargando…
CondenseNet with exclusive lasso regularization
Group convolution has been widely used in deep learning community to achieve computation efficiency. In this paper, we develop CondenseNet-elasso to eliminate feature correlation among different convolution groups and alleviate neural network’s overfitting problem. It applies exclusive lasso regular...
Autores principales: | Ji, Lizhen, Zhang, Jiangshe, Zhang, Chunxia, Ma, Cong, Xu, Shuang, Sun, Kai |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer London
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8236312/ https://www.ncbi.nlm.nih.gov/pubmed/34219978 http://dx.doi.org/10.1007/s00521-021-06222-0 |
Ejemplares similares
-
Manifold regularization for sparse unmixing of hyperspectral images
por: Liu, Junmin, et al.
Publicado: (2016) -
Seagull: lasso, group lasso and sparse-group lasso regularization for linear regression models via proximal gradient descent
por: Klosa, Jan, et al.
Publicado: (2020) -
Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions
por: Ogutu, Joseph O, et al.
Publicado: (2012) -
Graph-regularized dual Lasso for robust eQTL mapping
por: Cheng, Wei, et al.
Publicado: (2014) -
Factors Affecting Exclusive Breastfeeding, Using Adaptive LASSO Regression
por: Maharlouei, Najmeh, et al.
Publicado: (2018)