Temporal augmentation for SNNs

Augmentation is an important part of training deep neural nets these days. Whereas convolutional neural networks typically use spatial augmentation techniques such as rotation, shifting and other affine transforms, data for spiking neural networks often has an important temporal component. I'd be interested in exploring specifically temporal augmentation techniques on spikes. The tooling for that is already in a very mature state in the form of Tonic, please check it out here:

Go to group wiki Go to wiki users Info


Day Time Location
Wed, 04.05.2022 16:00 - 16:30 Lecture room
Mon, 09.05.2022 22:00 - 23:00 Disco lab
Fri, 06.05.2022 21:00 - 22:00 Disco lab


Gregor Lenz


Yeshwanth Bethi
Giulia D'angelo
Nik Dennler
Jakub Fil
Julian Goeltz
James Knight
Laura Kriener
Gregor Lenz
Thomas Nowotny
James Turner