Random Feature Spiking Neural Networks

ICLR 2026 Conference Submission19633 Authors

Keywords: Spiking Neural Networks, Random Feature Methods, Time Series Forecasting

TL;DR: We propose a data-driven random feature algorithm for SNNs to be used as initialisation or standalone training strategy.

Abstract: Spiking Neural Networks (\textit{SNN}s) as Machine Learning (\textit{ML}) models have recently received a lot of attention as a potentially more energy-efficient alternative to conventional Artificial Neural Networks. The non-differentiability and sparsity of the spiking mechanism can make these models very difficult to train with algorithms based on propagating gradients through the spiking non-linearity. We address this problem by adapting the paradigm of Random Feature Methods (\textit{RFM}s) from Artificial Neural Networks (\textit{ANN}s) to Spike Response Model (\textit{SRM}) \textit{SNN}s. This approach allows training of \textit{SNN}s without approximation of the spike function gradient. Concretely, we propose a novel data-driven, fast, high-performance, and interpretable algorithm for end-to-end training of \textit{SNN}s inspired by the \textit{SWIM} algorithm for \textit{RFM}-\textit{ANN}s, which we coin \textit{S-SWIM}. We provide a thorough theoretical discussion and supplementary numerical experiments showing that \textit{S-SWIM} can reach high accuracies on time series forecasting as a standalone strategy and serve as an effective initialisation strategy before gradient-based training. Additional ablation studies show that our proposed method performs better than random sampling of network weights.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 19633