SNUFA 2023

Brief summary. 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.

Executive committee. Emre Neftci, Charlotte Frenkel, Dan Goodman, and Friedemann Zenke.

Quick links. Recorded talks on Youtube

Key information

Workshop. 7-8 November 2023, European afternoons (online).

Recorded talks (Youtube)

Registration. Closed.

Abstract submission. Closed.

Invited speakers. Rodolphe Sepulchre (KU Leuven and University of Cambridge), Melika Payvand (INI, Zurich), Gabriel Ocker (Boston University), Jeff Krichmar (UC Irvine)

Agenda

Click here for all abstracts.

Click here to open in Google Calendar (allows you to add to your own calendar).

Time (CET) Session Local date/time
November 7th    
14:00 Welcome by the organizers
  Session 1 (Chair: Charlotte Frenkel)  
14:10 Rodolphe Sepulchre, KU Leuven and University of Cambridge (invited)
Neuromorphic learning: a control perspective
14:55 Veronika Koren
Efficient computing of high-dimensional neural representations with biologically plausible E-I spiking networks
15:15 Alessio Quaresima, Hartmut Fitz, Renato Duarte, Peter Hagoort, Karl Magnus Petersson
Dendrites support formation and reactivation of sequential memories through Hebbian plasticity
15:35 Break (30mins)  
  Session 2 (Chair: Friedemann Zenke)  
16:05 Gabriel Ocker, Boston University (invited)
Plasticity, activity, and computation in neuronal networks
16:50 Maayan Levy & Tim P. Vogels
Capacity of a spiking network with preserved weight distribution: a game-theory-inspired study
17:10 Flash talks by selected poster presenters
Watch on Youtube
17:30 Break (30mins)
18:00 Poster session (Zoom)
Poster link for registered participants
November 8th    
14:00 Welcome to day two
  Session 3 (Chair: Dan Goodman)  
14:05 Melika Payvand, INI, Zurich (invited)
Analog substrates for temporal and local event-based computation
14:50 Ilyass Hammouamri, Ismail Khalfaoui Hassani, Timothée Masquelier
Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
15:10 Justus Huebotter, Pablo Lanillos, Serge Thill, Marcel van Gerven
Training Spiking Neural Networks for Continuous Control with Surrogate Gradients
15:30 Break (30mins)
  Session 4 (Chair: Emre Neftci)  
16:00 Jeff Krichmar, UC Irvine (invited)
CARLSim: An Open-Source Community Resource for Large-Scale, Detailed Spiking Neural Network Research and Development
16:45 Alexander Efremov, Martino Sorbaro, Pau Vilimelis Aceituno, Benjamin Grewe
Training fast spiking networks through STDP and control feedback
17:05 Antony W. N’dri, Céline Teulière and Jochen Triesch
Combining various types of spike timing-dependent plasticity to learn efficient neural codes
17:25 Closing remarks by the organizers

Abstract submissions

Closed

Abstracts will be made publicly available at the end of the abstract submissions deadline for blinded public comments and ratings. We will select the most highly rated abstracts for contributed talks and flash talks, subject to maintaining a balance between the different fields of, broadly speaking, neuroscience, computer science and neuromorphic engineering. Abstracts not selected for a talk, and abstracts selected for a flash talk, will be presented as posters.

Format