Skip to content

Zenke Lab

Computational Neuroscience at the FMI

  • The Zenke Lab
  • Publications
  • Research
    • Dynamic networks through orchestrated plasticity
    • Functional spiking neural networks through surrogate gradients
    • Inhibitory microcircuits and predictive processing
    • Role of internal synaptic dynamics for memory consolidation and continual learning
  • Seminars
  • Posts
  • Team
  • Jobs
  • Contact
October 25, 2020January 11, 2021 fzenkepublications

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

September 26, 2020September 30, 2020 fzenkeconferences, poster

Kris and Claire present exciting excitation-inhibition work at the Bernstein conference

Both Claire and Kris will present virtual posters about their modeling work in the olfactory system. If you are interested in learning more about what precise EI balance and transient attractor states have to doContinue reading

September 1, 2020October 6, 2020 fzenkejobs

Hiring: Information processing in spiking neural networks

We are looking for Ph.D. students to work on the computational principles of information processing in spiking neural networks. The project strives to understand computation in the sparse spiking and sparse connectivity regime, in whichContinue reading

August 6, 2020September 2, 2020 fzenkeconferences, News

Online workshop: Spiking neural networks as universal function approximators

Dan Goodman and myself are organizing an online workshop on new approaches to training spiking neural networks, Aug 31st / Sep 1st 2020. Invited speakers: Sander Bohte (CWI), Iulia M. Comsa (Google), Franz Scherr (TUG), Emre Neftci (UC Irvine),Continue reading

June 16, 2020June 17, 2020 fzenkepublications

Paper: Finding sparse trainable neural networks through Neural Tangent Transfer

New paper led by Tianlin Liu on “Finding sparse trainable neural networks through Neural Tangent Transfer” https://arxiv.org/abs/2006.08228  (and code) which was accepted at ICML. In the paper we leverage the neural tangent kernel to instantiate sparse neuralContinue reading

June 15, 2020June 15, 2020 fzenkepublications

Preprint: Training spiking multi-layer networks with surrogate gradients on an analog neuromorphic substrate

We are happy to share our new preprint “Training spiking multi-layer networks with surrogate gradients on an analog neuromorphic substrate” (https://arxiv.org/abs/2006.07239). This work led by Benjamin Cramer and Sebastian Billaudelle and is a joint effortContinue reading

February 5, 2020June 16, 2020 fzenketalk

Talk: Bench to Bedside Symposium at Uni Basel

On Friday 7th February 2020, 09:00, Friedemann will talk about “Building functional neural networks in-silico” at the Bench to Bedside Symposium at Uni Basel Pharmazentrum, Hörsaal 1, Klingelbergstrasse 50/70, 4056 Basel.

November 8, 2019February 25, 2020 fzenkepublications

Paper: Surrogate Gradient Learning in Spiking Neural Networks

“Bringing the Power of Gradient-based optimization to spiking neural networks” We are happy to announce that our tutorial paper on Surrogate Gradient Learning in spiking neural networks now appeared in the IEEE Signal Processing Magazine.Continue reading

October 29, 2019October 29, 2019 fzenkepublications

Perspective: A deep learning framework for neuroscience

Our perspective paper on how systems neuroscience can benefit from deep learning was published today. In work led by Blake Richards, Tim Lillicrap, and Konrad Kording, we argue that focusing on the three core elements usedContinue reading

October 28, 2019December 31, 2020 fzenkepublications

Preprint: The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks

Update (2020-12-30) Now published: Cramer, B., Stradmann, Y., Schemmel, J., and Zenke, F. (2020). The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks. IEEE Transactions on Neural Networks and Learning SystemsContinue reading

Posts navigation

Older posts

Links

  • CompNeuro Initiative Basel
  • PhD program
  • See also fzenke.net and our FMI website
  • Review our privacy policy

Recent Posts

  • Paper: Brain-Inspired Learning on Neuromorphic Substrates
  • Kris and Claire present exciting excitation-inhibition work at the Bernstein conference
  • Hiring: Information processing in spiking neural networks
  • Online workshop: Spiking neural networks as universal function approximators
  • Paper: Finding sparse trainable neural networks through Neural Tangent Transfer
Proudly powered by WordPress | Theme: Oria by JustFreeThemes.