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
Category: publications
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
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
A tactile robotic finger tip and a spiking neural network read Braille
This fun project started as a summer student project at Telluride 2021 led and advised by Chiara Bartolozzi and myself. An incredibly motivated group of summer students taught a robotic fingertip with tactile sensors andContinue reading
Paper: Nonlinear transient amplification in recurrent neural networks with short-term plasticity
Update (21.12.2021): Now published https://elifesciences.org/articles/71263 I am pleased to share our new preprint: “Nonlinear transient amplification in recurrent neural networks with short-term plasticity” led by Yue Kris Wu in which we study possible mechanisms forContinue reading
Paper: Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits
We’re excited to see this published. A new take on spatial credit assignment in cortical circuits based on Richard Naud’s idea on burst multiplexing. A truly collaborative effort lead by Alexandre Payeur and Jordan GuerguievContinue reading
Publication: Visualizing a joint future of neuroscience and neuromorphic engineering
Happy to share this report summarizing the key contributions, discussion outcomes, and future research directions as presented at the spiking neural networks as universal function approximators meeting SNUFA2020. Paper: https://www.cell.com/neuron/fulltext/S0896-6273(21)00009-XAuthor link: https://authors.elsevier.com/a/1cbg3_KOmxI%7E6f
Paper: Brain-Inspired Learning on Neuromorphic Substrates
I’m happy to share our new overview paper (https://ieeexplore.ieee.org/document/9317744, preprint: arxiv.org/abs/2010.11931) on brain-inspired learning on neuromorphic substrates in (spiking) recurrent neural networks. We systematically analyze how the combination of Real-Time-Recurrent Learning (RTRL; Williams and Zipser,Continue reading
Preprint: The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks
We just put up a new preprint https://www.biorxiv.org/content/10.1101/2020.06.29.176925v1 in which we take a careful look at what makes surrogate gradients work. Spiking neural networks are notoriously hard to train using gradient-based methods due to theirContinue reading