Expressive Power of Recurrent Spiking Neural Networks for Sequence Modeling
Year: 2026
Type: article
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.
Source: Universitätsbibliothek der LMU
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225643488
FWCI:
Cites:
Cited by:
Related to: