Cédric Goemaere

Profile

Hi there, I'm Cédric.

I'm a PhD student at Ghent University and part of the T2K group, supervised by prof. Thomas Demeester.

My research focuses on developing stable machine learning algorithms for analog electronics. Specifically, I am currently working on scaling-up Predictive Coding models in a principled manner. Before this, I explored Hopfield networks, Equilibrium Propagation, and their connection with Deep Equilibrium Models (DEQs).

Oh yeah, I also have a blog that is probably more up-to-date.

Publications

Accelerating Hopfield Network Dynamics: Beyond Synchronous Updates and Forward Euler

Cédric Goemaere, Johannes Deleu, Thomas Demeester

“Machine Learning Meets Differential Equations: From Theory to Applications”, ECAI 2024

Accelerating Hierarchical Associative Memory: A Deep Equilibrium Approach

Cédric Goemaere, Johannes Deleu, Thomas Demeester

"Associative Memory & Hopfield Networks'', NeurIPS 2023

Exploring the Temperature-Dependent Phase Transition in Modern Hopfield Networks

Felix Koulischer, Cédric Goemaere, Tom Van Der Meersch, Johannes Deleu, Thomas Demeester

"Associative Memory & Hopfield Networks'', NeurIPS 2023