期刊论文详细信息
IEEE Access
Improving Neural Network With Uniform Sparse Connectivity
Weijun Luo1 
[1] Department of Bioinformatics and Genomics, College of Computing and Informatics, University of North Carolina (UNC) at Charlotte, Charlotte, NC, USA;
关键词: Neural network (NN);    fully connected network (FCN);    uniform sparse network (USN);    sparse network (SN);    machine learning (ML);    deep learning (DL);   
DOI  :  10.1109/ACCESS.2020.3040943
来源: DOAJ
【 摘 要 】

Neural network forms the foundation of deep learning and numerous AI applications. Classical neural networks are fully connected, expensive to train and prone to overfitting. Sparse networks tend to have convoluted structure search, suboptimal performance and limited usage. We proposed the novel uniform sparse network (USN) with even and sparse connectivity within each layer. USN has one striking property that its performance is independent of the substantial topology variation and enormous model space, thus offers a search-free solution to all above mentioned issues of neural networks. USN consistently and substantially outperforms the state-of-the-art sparse network models in prediction accuracy, speed and robustness. It even achieves higher prediction accuracy than the fully connected network with only 0.55% parameters and 1/4 computing time and resources. Importantly, USN is conceptually simple as a natural generalization of fully connected network with multiple improvements in accuracy, robustness and scalability. USN can replace the latter in a range of applications, data types and deep learning architectures. We have made USN open source at https://github.com/datapplab/sparsenet.

【 授权许可】

Unknown   

  文献评价指标  
  下载次数:0次 浏览次数:0次