Expressive Power of Recurrent Spiking Neural Networks for Sequence Modeling
MCML Authors
Massimiliano Datres
Dr.
Gitta Kutyniok
Prof. Dr.
Core PI
Abstract
Massimiliano Datres
Dr.
Gitta Kutyniok
Prof. Dr.
Core PI
Abstract
Spiking neural networks (SNNs) provide a biologically inspired and potentially efficient framework for processing sequential data, but their expressive power, particularly in the dynamical setting, remains poorly understood. We establish a universality result showing that recurrent SNNs can approximate a broad class of sequence-to-sequence mappings, thereby providing theoretical support for their use in temporal learning and time series processing.
inproceedings NDA+26
TSALM @ICLR 2026
Workshop on Time Series in the Age of Large Models at the 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available.Authors
D. A. Nguyen • M. Datres • E. Araya • G. KutyniokLinks
URLResearch Area
BibTeXKey: NDA+26