中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
  5. 类脑芯片与系统研究
Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application

文献类型：期刊论文

作者Wang, Peisong; He, Xiangyu; Cheng, Jian
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2022-05-27
页码13
关键词Quantization (signal) Deep learning Convolution Training Biological neural networks Optimization Neurons Acceleration binarized neural networks (BNNs) compression fixed-point quantization
ISSN号2162-237X
DOI10.1109/TNNLS.2022.3173498
通讯作者Cheng, Jian(jcheng@nlpria.ac.cn)
英文摘要While binarized neural networks (BNNs) have attracted great interest, popular approaches proposed so far mainly exploit the symmetric sign function for feature binarization, i.e., to binarize activations into -1 and +1 with a fixed threshold of 0. However, whether this option is optimal has been largely overlooked. In this work, we propose the Sparsity-inducing BNN (Si-BNN) to quantize the activations to be either 0 or +1, which better approximates ReLU using 1-bit. We further introduce trainable thresholds into the backward function of binarization to guide the gradient propagation. Our method dramatically outperforms the current state-of-the-art, lowering the performance gap between full-precision networks and BNNs on mainstream architectures, achieving the new state-of-the-art on binarized AlexNet (Top-1 50.5%), ResNet-18 (Top-1 62.2%), and ResNet-50 (Top-1 68.3%). At inference time, Si-BNN still enjoys the high efficiency of bit-wise operations. In our implementation, the running time of binary AlexNet on the CPU can be competitive with the popular GPU-based deep learning framework.
资助项目National Key Research and Development Program of China[2021ZD0201504] ; National Natural Science Foundation of China[61906193] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA27040300]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000805801000001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/49509]  
专题类脑芯片与系统研究
通讯作者Cheng, Jian
作者单位Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Peisong,He, Xiangyu,Cheng, Jian. Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:13.
APA Wang, Peisong,He, Xiangyu,&Cheng, Jian.(2022).Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA Wang, Peisong,et al."Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):13.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。