We are happy our new paper “Improving equilibrium propagation (EP) without weight symmetry through Jacobian homeostasis,” led by Axel accepted at ICLR 2024. Preprint: https://arxiv.org/abs/2309.02214Code: https://github.com/Laborieux-Axel/generalized-holo-ep EP prescribes a local learning rule and uses recurrentContinue reading
Tag: axel
Paper: Implicit variance regularization in non-contrastive SSL
New paper from the lab accepted at NeurIPS: “Implicit variance regularization in non-contrastive SSL.” In our article, first-authored by Manu and Axel, we add further understanding to how non-contrastive self-supervised learning (SSL) methods avoid collapse.Continue reading
Axel awarded an SNSF Swiss Postdoctoral Fellowship
Congratulations, Axel (woot woot), for being awarded an SNSF Swiss Postdoctoral Fellowship, the interim Swiss equivalent of a Marie Curie European Fellowship, to work on fundamental questions pertaining to neuronal circuit architectures and learning. WeContinue reading