Marcel van Gerven

🔸 Organisers: Wolfgang Maaß, Director at ELLIS Unit Graz & @marcelge, Director at @ellis_nijmegen 📅 Submit contributions by Oct 23, 2025 (AoE) 🔗 eurips.cc/ellis

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 ellis-unit-graz.github.io/workshops/

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. 👉 arxiv.org/pdf/2501.03051

Ornstein–Uhlenbeck Adaptation as a Mechanism for Learning in Brains and Machines mdpi.com/3099830 #mdpientropy via @Entropy_MDPI

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. arxiv.org/pdf/2405.02385

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! arxiv.org/abs/2203.13203

Associate prof position in AI @ Donders institute (assistant level also considered). Application deadline: 1 feb. ru.nl/werken/details…

AD bericht over ons onderzoek naar een hersenschorsprothese ad.nl/binnenland/ove…

Join the Intel Machine Learning Seminar powered by @deepsense_ai November 17th at @AI_Radboud. Sign up here: plan.seek.intel.com/intel-ai-acade… @pim @marcelge @IrisVanRooij @JohanKwisthout @francgrootjen

Our neural decoding work is in the featured IEEE Pulse article 'Reading Minds': pulse.embs.org/september-2017…

Open positions in cognitive AI! twitter.com/ccnlab/status/…