µL2Q - An Ultra-Low Loss Quantization Method for DNN Compression.
IJCNN(2019)
摘要
Data quantization has been proved to be an effective method to compress deep neural networks (DNNs) by using less bits to represent the parameters and intermediate data. The bit width of the data directly affects the memory footprint, computing capability, and energy consumption during the computation of the DNN models. Although there have been numerous existing studies on data quantization, there is still no quantitative analysis of the existing quantization methods, which results in empirical quantization with unpredictable DNN accuracy loss. To address this problem, we propose an effective method, called ultra-low loss quantization (µL2Q), to provide DNN quantization schemes based on comprehensive quantitative data analysis. µL2Q builds the transformation of the original data to a data space with standard normal distribution, and then find the optimal parameters to minimize the loss of the quantization …
更多查看译文
关键词
μL2Q,DNN quantization schemes,comprehensive quantitative data analysis,data space,targeted bit width,compression ratio,ultra-low loss quantization method,data quantization,deep neural networks,DNN models,unpredictable DNN accuracy loss,ultra-low loss quantization,DNN compression designs,end-to-end DNN design,standard normal distribution,machine learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络