5 citations · 6 across the 2 of their papers we have counts for
Showing eess.SPShow all
2 papers · 1 filter
eess.SP2020
Low Precision Floating-point Arithmetic for High Performance FPGA-based CNN Acceleration
Chen Wu, Mingyu Wang, Xinyuan Chu +2
Low precision data representation is important to reduce storage size and memory access for convolutional neural networks (CNNs). Yet, existing methods have two major limitations:…
eess.SP2020★ 5 cited
Phoenix: A Low-Precision Floating-Point Quantization Oriented Architecture for Convolutional Neural Networks
Chen Wu, Mingyu Wang, Xiayu Li +3
Convolutional neural networks (CNNs) achieve state-of-the-art performance at the cost of becoming deeper and larger. Although quantization (both fixed-point and floating-point) has…