# Random Feature Spiking Neural Networks

arXiv: https://arxiv.org/abs/2510.01012 · HTML: https://mlsanity.com/paper/2510.01012/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 54 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 28 of 28)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks](https://mlsanity.com/paper/1910.07407/) (2019)
- [Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings](https://mlsanity.com/paper/2306.17670/) (2023)
- [Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction](https://mlsanity.com/paper/2409.00265/) (2024)
- [Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks](https://mlsanity.com/paper/2005.11633/) (2020)
- [Deep Randomized Neural Networks](https://mlsanity.com/paper/2002.12287/) (2020)
- [Dilated convolution with learnable spacings](https://mlsanity.com/paper/2112.03740/) (2021)
- [Sampling weights of deep neural networks](https://mlsanity.com/paper/2306.16830/) (2023)
- [Fluctuation-driven initialization for spiking neural network training](https://mlsanity.com/paper/2206.10226/) (2022)
- [Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks](https://mlsanity.com/paper/2401.04486/) (2024)
- [Co-learning synaptic delays, weights and adaptation in spiking neural networks](https://mlsanity.com/paper/2311.16112/) (2023)
- [Reconsidering the Energy Efficiency of Spiking Neural Networks Inference from Analytical Perspectives](https://mlsanity.com/paper/2409.08290/) (2024)
- [Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition](https://mlsanity.com/paper/2302.08607/) (2023)
- [Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient](https://mlsanity.com/paper/2304.13098/) (2023)
- [Elucidating the theoretical underpinnings of surrogate gradient learning in spiking neural networks](https://mlsanity.com/paper/2404.14964/) (2024)
- [Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks](https://mlsanity.com/paper/2406.00405/) (2024)
- [Loss Landscape Characterization of Neural Networks without Over-Parametrization](https://mlsanity.com/paper/2410.12455/) (2024)
- [Koopman-informed recurrent neural networks](https://mlsanity.com/paper/2410.23467/) (2024)
- [Capturing the dynamical repertoire of single neurons with generalized linear models](https://mlsanity.com/paper/1602.07389/) (2016)
- [SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) Complexity](https://mlsanity.com/paper/2505.10352/) (2025)
- [Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators](https://mlsanity.com/paper/2405.14362/) (2024)
- [Toward Relative Positional Encoding in Spiking Transformers](https://mlsanity.com/paper/2501.16745/) (2025)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) as Machine Learning (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 (RFMs) from Artificial Neural Networks (ANNs) to Spike Response Model (SRM) SNNs. This approach allows training of SNNs 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 SNNs inspired by the SWIM algorithm for RFM-ANNs, which we coin S-SWIM. We provide a thorough theoretical discussion and supplementary numerical experiments showing that 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.