18 citations · 21 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021★ 2 cited
Post-Training Sparsity-Aware Quantization
Gil Shomron, Freddy Gabbay, Samer Kurzum +1
Quantization is a technique used in deep neural networks (DNNs) to increase execution performance and hardware efficiency. Uniform post-training quantization (PTQ) methods are comm…
cs.LG2020★ 18 cited
HCM: Hardware-Aware Complexity Metric for Neural Network Architectures
Alex Karbachevsky, Chaim Baskin, Evgenii Zheltonozhskii +4
Convolutional Neural Networks (CNNs) have become common in many fields including computer vision, speech recognition, and natural language processing. Although CNN hardware acceler…