Joint Optimization of Dimension Reduction and Mixed-Precision Quantization for Activation Compression of Neural Networks

Yu-Shan Tai, Cheng-Yang Chang, Chieh-Fang Teng, Yi-Ta Chen, An-Yeu Wu. Joint Optimization of Dimension Reduction and Mixed-Precision Quantization for Activation Compression of Neural Networks. IEEE Trans. on CAD of Integrated Circuits and Systems, 42(11):4025-4037, November 2023. [doi]

Abstract

Abstract is missing.