Quantized CNN: A Unified Approach to Accelerate and Compress Convolutional Networks.
IEEE Transactions on Neural Networks and Learning Systems(2018)
摘要
We are witnessing an explosive development and widespread application of deep neural networks (DNNs) in various fields. However, DNN models, especially a convolutional neural network (CNN), usually involve massive parameters and are computationally expensive, making them extremely dependent on high-performance hardware. This prohibits their further extensions, e.g., applications on mobile devices....
更多查看译文
关键词
Convolutional codes,Acceleration,Quantization (signal),Computational modeling,Mobile handsets,Training,Tensile stress
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要