DelGrad: exact event-based gradients for training delays and weights on spiking neuromorphic hardware

Julian Göltz (), Jimmy Weber (), Laura Kriener (), Sebastian Billaudelle, Peter Lake, Johannes Schemmel, Melika Payvand () and Mihai A. Petrovici ()
Additional contact information
Julian Göltz: Heidelberg University
Jimmy Weber: University of Zurich and ETH Zurich
Laura Kriener: University of Bern
Sebastian Billaudelle: Heidelberg University
Peter Lake: Heidelberg University
Johannes Schemmel: Heidelberg University
Melika Payvand: University of Zurich and ETH Zurich
Mihai A. Petrovici: University of Bern

Nature Communications, 2025, vol. 16, issue 1, 1-10

Abstract: Abstract Spiking neural networks (SNNs) inherently rely on the timing of signals for representing and processing information. Augmenting SNNs with trainable transmission delays, alongside synaptic weights, has recently shown to increase their accuracy and parameter efficiency. However, existing training methods to optimize such networks rely on discrete time, approximate gradients, and full access to internal variables such as membrane potentials. This limits their precision, efficiency, and suitability for neuromorphic hardware due to increased memory and I/O-bandwidth demands. Here, we propose DelGrad, an analytical, event-based training method to compute exact loss gradients for both weights and delays. Grounded purely in spike timing, DelGrad eliminates the need to track any other variables to optimize SNNs. We showcase this key advantage by implementing DelGrad on the BrainScaleS-2 mixed-signal neuromorphic platform. For the first time, we experimentally demonstrate the parameter efficiency, accuracy benefits, and stabilizing effect of adding delays to SNNs on noisy hardware. DelGrad thus provides a new way for training SNNs with delays on neuromorphic substrates, with substantial improvements over previous results.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-63120-y Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-63120-y

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-63120-y

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().