Efficient event-based delay learning in spiking neural networks

Balázs Mészáros (), James C. Knight and Thomas Nowotny ()
Additional contact information
Balázs Mészáros: University of Sussex, Sussex AI, School of Engineering and Informatics
James C. Knight: University of Sussex, Sussex AI, School of Engineering and Informatics
Thomas Nowotny: University of Sussex, Sussex AI, School of Engineering and Informatics

Nature Communications, 2025, vol. 16, issue 1, 1-14

Abstract: Abstract Spiking Neural Networks compute using sparse communication and are attracting increased attention as a more energy-efficient alternative to traditional Artificial Neural Networks. While standard Artificial Neural Networks are stateless, spiking neurons are stateful and hence intrinsically recurrent, making them well-suited for spatio-temporal tasks. However, the duration of this intrinsic memory is limited by synaptic and membrane time constants. Delays are a powerful additional mechanism and, in this paper, we propose an event-based training method for Spiking Neural Networks with delays, grounded in the EventProp formalism, which enables the calculation of exact gradients with respect to weights and delays. Our method supports multiple spikes per neuron and introduces a delay learning algorithm that can, in contrast to previous methods, also be applied to recurrent Spiking Neural Networks. We evaluate our method on a simple sequence detection task, as well as the Yin-Yang, Spiking Heidelberg Digits, Spiking Speech Commands and Braille letter reading datasets, demonstrating that our algorithm can optimise delays from suboptimal initial conditions and enhance classification accuracy compared to architectures without delays. We also find that recurrent delays are particularly beneficial in small networks. Finally, we show that our approach uses less than half the memory of the current state-of-the-art delay-learning method and is up to 26 × faster.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-65394-8 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_s41467-025-65394-8

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

DOI: 10.1038/s41467-025-65394-8

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 ().