Recent efforts have fostered significant progress towards deep learning in spiking networks, both theoretical and in silico. Here, we discuss several different approaches, including a tentative comparison of the results on BrainScaleS-2, and hint towards future such comparative studies.
@article{arxiv.2309.10823,
title = {Gradient-based methods for spiking physical systems},
author = {Julian Göltz and Sebastian Billaudelle and Laura Kriener and Luca Blessing and Christian Pehle and Eric Müller and Johannes Schemmel and Mihai A. Petrovici},
journal= {arXiv preprint arXiv:2309.10823},
year = {2023}
}
Comments
2 page abstract, submitted to and accepted by the NNPC (International conference on neuromorphic, natural and physical computing)