45 citations · 70 across the 3 of their papers we have counts for
3 papers
cs.LG2022★ 4 cited
PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
Sanghoon Myung, In Huh, Wonik Jang +5
Inductive transfer learning aims to learn from a small amount of training data for the target task by utilizing a pre-trained model from the source task. Most strategies that invol…
eess.SP2022★ 21 cited
Restructuring TCAD System: Teaching Traditional TCAD New Tricks
Sanghoon Myung, Wonik Jang, Seonghoon Jin +3
Traditional TCAD simulation has succeeded in predicting and optimizing the device performance; however, it still faces a massive challenge - a high computational cost. There have b…
cs.LG2021★ 45 cited
Learning Student-Friendly Teacher Networks for Knowledge Distillation
Dae Young Park, Moon-Hyun Cha, Changwook Jeong +2
We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on e…