SNUFA 2021
Like last year this online workshop brings together researchers in the fields of computational neuroscience, machine learning, and neuromorphic engineering to present their work and discuss ways of translating these findings into a better understanding of neural circuits. Topics include artificial and biologically plausible learning algorithms and the dissection of trained spiking circuits toward understanding neural processing. We have a manageable number of talks with ample time for discussions.
This year’s executive committee comprised Chiara Bartolozzi, Sander Bohté, Dan Goodman, and Friedemann Zenke.
The workshop took place 2-3 November, 2021.
Thanks to World Wide Neuro for sponsoring this event!
Talks
Talks can be viewed on Crowdcast or YouTube.
Agenda
List of abstracts
| Time (CET) | Session | Local date/time |
|---|---|---|
| November 2nd | ||
| 14:00 | Welcome by the organizers | |
| Session 1 (Chair: Chiara Bartolozzi) | ||
| 14:10 | Tara Hamilton, University of Technology Sydney, Australia (invited talk) Unsupervised Spiking Neural Networks |
|
| 14:55 | Dominik Dold, ESA ESTEC, Germany Spike-based embeddings for multi-relational graph data abstract |
|
| 15:15 | Ulysse Rancon, U Bordeaux, France StereoSpike: Depth Learning with a Spiking Neural Network abstract |
|
| 15:35 | Break (30mins) | |
| Session 2 (Chair: Friedemann Zenke) | ||
| 16:05 | Henning Sprekeler, TU Berlin, Germany (invited talk) Optimising spiking interneuron circuits for compartment-specific feedback inhibition |
|
| 16:50 | Viola Priesemann, MPI-DS, Germany Deriving local synaptic learning rules for efficient representations in networks of spiking neurons abstract |
|
| 17:10 | Nicolas Perez-Nieves, Imperial Understanding the role of neural heterogeneity in learning abstract |
|
| 17:30 | Break (30mins) | |
| 18:00 | Panel debate (Zoom) | |
| November 3rd | ||
| 14:00 | Welcome | |
| Session 3 (Chair: Sander Bohte) | ||
| 14:10 | Dylan Muir, SynSense, Switzerland (invited talk) Machine Learning with SNNs, for low-power inference on neuromorphic hardware |
|
| 14:55 | Julia Gygax, FMI, Switzerland Optimal initialization strategies for Deep Spiking Neural Networks abstract |
|
| 15:15 | Christian Pehle, Uni Heidelberg, Germany Event-based Backpropagation for Exact Gradients in Spiking Neural Networks abstract |
|
| 15:35 | Break (15mins) | |
| 15:50 | Poster session (40mins) In individual Zoom rooms |
|
| Session 4 (Chair: Dan Goodman) | ||
| 16:30 | Catherine Schuman, Oak Ridge National Laboratory, USA (invited talk) Evolutionary Optimization for Spiking Neural Networks and Neuromorphic Computing |
|
| 17:15 | James Knight, University of Sussex, UK Efficient GPU training of SNNs using approximate RTRL abstract |
|
| 17:35 | Jens Egholm Pedersen, KTH, Sweden Norse: A library for gradient-based learning in Spiking Neural Networks abstract |
|
| 17:55 | Closing remarks by organizers |
Format
- Two half days (CEST afternoons)
- 4 invited talks
- 8 contributed talks
- Poster session
- Panel debate: “What should be the next big breakthrough in spiking neural networks?”
Last year’s workshop
You can read last year’s meeting report here, watch last year’s talks and discussions on Crowdcast or YouTube.