🔸 Organisers: Wolfgang Maaß, Director at ELLIS Unit Graz & @marcelge, Director at @ellis_nijmegen
📅 Submit contributions by Oct 23, 2025 (AoE)
🔗 https://t.co/8VRXUVkkzv
Join us for the ELLIS UnConference Workshop on Energy-Efficient AI: Models, Algorithms, and Hardware for Sustainable Intelligence taking place in Copenhagen 🇩🇰 on December 2, 2025 at the Bella Center, co-located with #EurIPS https://t.co/lO27mpt8ZB
Our new reconstruction paper using Inverse Receptive Field Attention (IRFA) is online!
IRFA reconstructs images and visualizes feature and spatial Inverse Receptive Fields. The architecture does not rely on pre-trained models.
👉 https://t.co/cpZLTYsJXe
As AI adoption becomes more widespread, so do concerns about its energy consumption. Our latest paper proposes a method to train AI models more efficiently. The method reduces energy use by more than half when training a ResNet-18 model on ImageNet. https://t.co/HF3q2rgcaF
We (Nasir Ahmad; @nasiryahm , Ellen Schrader & Marcel van Gerven @marcelge) are proud to share our recent paper: Constrained Parameter Inference as a Principle for Learning! https://t.co/wDLstE62Jh