.png){kind=icon}
返回
Designing efficient convolutional neural network structure: A survey
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.08.158.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Asa powerful machine learning method, deep learning has attracted the attention of numerous research -ers. While exploring a high-performance neural network model, the floating-point operations of a neural network model are also increasing. In recent years, many researchers have noticed that efficiency is also one of important indicators to measure the property of neural network models. Obviously, the efficient neural network model is more helpful to deploy on mobile and embedded devices. Therefore, the efficient neural network model becomes a hot research spot. In this paper, we review the methods related to the structural design of efficient convolution neural networks in recent years. According to the characteristics of these methods, we divide them into three kinds of methods: model pruning, efficient architecture, and neural architecture search. Detailed analyses of each method are presented to demonstrate their advan-tages and disadvantages. Then, we comprehensively compare them in detail and propose many sugges-tions about the design of the efficient convolution neural network model structure. Inspired by these suggestions, we built a new efficient neural network model, SharedNet. And the SharedNet obtains the best accuracy of manually-designed efficient CNN models on the ImageNet dataset.(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Deep learning
Model structure design
Efficient convolution
Neural architecture search
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Sustaining the efficiency of the Fe(0)/H2O system for Cr(VI) removal by MnO2 amendment.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏Capsule Network Based Modeling of Multi-omics Data for Discovery of Breast Cancer-Related Genes基于胶囊网络的多组学数据建模及乳腺癌相关基因的发现
PREAI
分享收藏Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptors
OAAI
OAAI分享收藏Recurrent Neural Network for Predicting Transcription Factor Binding Sites预测转录因子结合位点的递归神经网络SCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏Distant regulatory elements in a Sox10‐βGEO BAC transgene are required for expression of Sox10 in the enteric nervous system and other neural crest‐derived tissuesSox10-βgeo BAC转基因中的远距离调控元件是肠神经系统和其他神经源性组织中 Sox10 表达所必需的OAAI
OAAI分享收藏
查看更多内容