Prati
Deokki Hong
Deokki Hong
Sapeon Korea Inc.
Potvrđena adresa e-pošte na sapeon.com
Naslov
Citirano
Citirano
Godina
Qimera: Data-free quantization with synthetic boundary supporting samples
K Choi, D Hong, N Park, Y Kim, J Lee
Advances in Neural Information Processing Systems 34, 14835-14847, 2021
692021
Dance: Differentiable accelerator/network co-exploration
K Choi, D Hong, H Yoon, J Yu, Y Kim, J Lee
2021 58th ACM/IEEE Design Automation Conference (DAC), 337-342, 2021
552021
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
K Choi, HY Lee, D Hong, J Yu, N Park, Y Kim, J Lee
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
422022
Online boundary-free continual learning by scheduled data prior
H Koh, M Seo, J Bang, H Song, D Hong, S Park, JW Ha, J Choi
The Eleventh International Conference on Learning Representations, 2023
202023
Enabling hard constraints in differentiable neural network and accelerator co-exploration
D Hong, K Choi, HY Lee, J Yu, N Park, Y Kim, J Lee
Proceedings of the 59th ACM/IEEE Design Automation Conference, 589-594, 2022
42022
ConCoDE: Hard-constrained Differentiable Co-Exploration Method for Neural Architectures and Hardware Accelerators
D Hong, K Choi, HY Lee, J Yu, Y Kim, N Park, J Lee
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–6