In Julian’s new paper “Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity“ accepted at NeurIPS we look at how to reconcile normative theories of gradient-based learning in the brain with phenomenological models ofContinue reading
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
Paper: Latent Predictive Learning
Our paper “The combination of Hebbian and predictive plasticity learns invariant object representations in deep sensory networks” is now published in Nature Neuroscience. https://www.nature.com/articles/s41593-023-01460-y Sensory networks in our brain represent environmental objects as points onContinue reading
Bernstein Conference 2023
Our lab is present at the Bernstein Conference in Berlin. Come and find us at the following posters: II 313: A comparative analysis of spiking network training with surrogate gradients and likelihood-based approaches Gygax J &Continue reading
New preprint: Improving equilibrium propagation without weight symmetry
I am happy to announce our new preprint on “Improving equilibrium propagation (EP) without weight symmetry through Jacobian homeostasis,” led by Axel. https://arxiv.org/abs/2309.02214 EP prescribes a local learning rule and uses recurrent dynamics for creditContinue reading
Welcome Atena and Mattias
The lab grows. We are all thrilled about the recent arrival of our new lab members: Atena and Mattias. Welcome! Glad to have you on board 🙂
SNUFA 2023
For all spiking neural network lovers out there, make sure to block November 7-8 in your agenda and submit a 300-word abstract to SNUFA 2023: https://snufa.net/2023 Invited speakers this year include: In previous years weContinue reading
Doctoral Class in Neurophysics
Professor Wulfram Gerstner and Professor Sahand Rahi at EPFL are co-organizing a class in neurophysics for doctoral students this year at EPFL. Friedemann will teach a set of lectures/tutorials on dynamic mean field theory inContinue reading
Swiss Computational Neuroscience Retreat 2023
After last year’s success, we repeated the Swiss Computational Neuroscience Retreat this year. The retreat attracted community members from Basel, Bern, Geneva, Lausanne, and Zurich, who convened for an intensive three-day event filled with talksContinue reading