Gradient-based methods for spiking physical systems
Julian G\"oltz, Sebastian Billaudelle, Laura Kriener, Luca Blessing,, Christian Pehle, Eric M\"uller, Johannes Schemmel, Mihai A. Petrovici
TL;DR
This paper reviews gradient-based methods for training spiking physical systems, highlighting recent progress and comparing results on BrainScaleS-2 to guide future research in this area.
Contribution
It provides a comparative overview of various gradient-based approaches for spiking systems and discusses preliminary results on BrainScaleS-2.
Findings
Progress in deep learning with spiking networks
Comparison of methods on BrainScaleS-2 platform
Suggestions for future comparative studies
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Memory and Neural Computing · Neural dynamics and brain function · Functional Brain Connectivity Studies
MethodsHierarchical Information Threading