ホーム
探索
nav.journalClub
トレンド
その他
synapse
⌘+K
言語
日本語
日本語
MADA-Unet: MultiRes-scale attentive dense-aggregating Unet for worst-case transient IR-drop prediction | Synapse
March 3, 2026
MADA-Unet: MultiRes-scale attentive dense-aggregating Unet for worst-case transient IR-drop prediction
YJ
Yuanfa Ji
Association of Southeast Asian Nations
MZ
Mingfeng Zhong
XS
Xiyan Sun
See all
Key Points
Worst-case transient IR-drop predictions showed significant accuracy improvements using MADA-Unet.
The model predicted IR-drop variations with a notable error reduction of 15% across tested scenarios.
MADA-Unet employs a multi-resolution architecture combined with attention mechanisms for efficient learning.
This approach highlights the need for advanced modeling techniques in power integrity assessments.
Mark Helpful
Like
Save
Bookmark
Relay
Share
Cite This Study
Copy
Ji et al. (Thu,) studied this question.
synapsesocial.com/papers/69a767c2badf0bb9e87e23a7
https://doi.org/https://doi.org/10.1016/j.mejo.2026.107097
Mark Helpful
Like
Save
Bookmark
Relay
Share