AirNN: A Featherweight Framework for Dynamic Input-Dependent Approximation of CNNs
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems(2021)
摘要
In this work, we propose AirNN, a novel framework which enables dynamic approximation of an already-trained convolutional neural network (CNN) in hardware during inference. AirNN enables input-dependent approximation of the CNN to achieve energy saving without much degradation in its classification accuracy at runtime. For each input, AirNN uses only a fraction of the CNN’s weights based on that i...
更多查看译文
关键词
Hardware,Clustering algorithms,Approximation algorithms,Neurons,Degradation,Neural networks,Inference algorithms
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要