5 citations · 9 across the 2 of their papers we have counts for
Showing cs.NEShow all
2 papers · 1 filter
cs.NE2019★ 5 cited
A Simple Method to Reduce Off-chip Memory Accesses on Convolutional Neural Networks
Doyun Kim, Kyoung-Young Kim, Sangsoo Ko +1
For convolutional neural networks, a simple algorithm to reduce off-chip memory accesses is proposed by maximally utilizing on-chip memory in a neural process unit. Especially, the…
cs.NE2018★ 4 cited
Convolutional Neural Network Quantization using Generalized Gamma Distribution
Doyun Kim, Han Young Yim, Sanghyuck Ha +2
As edge applications using convolutional neural networks (CNN) models grow, it is becoming necessary to introduce dedicated hardware accelerators in which network parameters and fe…