Dear Workshop participant, please use the local workshop instance @ http://www.capocaccia.hdp.
Until May 16 a one-way sync from the local instance to capocaccia.cc will be in place.

Fast and energy-efficient neuromorphic deep learning with spike times

Deep Learning with spiking neural networks is a hot topic in general and specifically in the neuromorphic field. In this workshop we will work together on applying and extending an algorithm that allows exact error-backpropagation in networks of LIF neurons (https://www.nature.com/articles/s42256-021-00388-x respectively https://arxiv.org/abs/1912.11443).
As a starting point, we provide insights into the theoretical aspect as well as an image classification example on the BrainScaleS-2 system, but are interested in collaborating on different applications and with other neuromorphic platforms.

Preparation: If you want to try out the code in simulation please clone the repository https://github.com/JulianGoeltz/fastAndDeep and follow the installation instructions in the README.

Go to group wiki Go to wiki users Info

Timetable

Day Time Location
Wed, 04.05.2022 14:30 - 15:00 Disco (Lab)
Fri, 06.05.2022 15:00 - 16:00 Disco

Moderator

Julian Goeltz
Laura Kriener

Members

Younes Bouhadjar
Matteo Cartiglia
Jörg Conradt
Giulia D'angelo
Julian Goeltz
Robert Gowers
Joscha Ilmberger
Efstathios Kagioulis
Laura Kriener
Gregor Lenz
Dylan Muir
Thomas Nowotny
Paul Pfeiffer
Martino Sorbaro
Yannik Stradmann
Simon Thorpe
James Turner