36 citations · 36 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022★ 36 cited
On-device Training: A First Overview on Existing Systems
Shuai Zhu, Thiemo Voigt, JeongGil Ko +1
The recent breakthroughs in machine learning (ML) and deep learning (DL) have catalyzed the design and development of various intelligent systems over wide application domains. Whi…
cs.LG2022
Fast Monte-Carlo Approximation of the Attention Mechanism
Hyunjun Kim, JeongGil Ko
We introduce Monte-Carlo Attention (MCA), a randomized approximation method for reducing the computational cost of self-attention mechanisms in Transformer architectures. MCA explo…