Pruning-aware Sparse Regularization for Network Pruning Structural neural network pruning aims to remove the redundant channels in the deep convolutional neural networks(CNNs)by pruning the filters of less impor... NF Jiang,X Zhao,CY Zhao,... - 机器智能研究:英文版 被引量: 0发表: 2023年 加载...
摘要 Pruning methods have shown to be effective at reducing the size of deep neural networks while keeping accuracy almost... 出版源 IEEE , 2019 关键词 Deep Learning / Recognition: Detection / Categorization / Retrieval / Vision Applications and Systems ...
In this paper, a novel smooth group L1/2 (SGL1/2) regularization method is proposed for pruning hidden nodes of the fully connected layer in convolution neural networks. Usually, the selection of nodes and weights is based on experience, and the convolut