Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing

arXiv:2604.08624v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) are naturally suited for speech processing tasks due to their specific dynamics, which allows them to handle temporal data. However, the threshold-based generation of spikes in SNNs intuitively causes an angular or irregular predictive landscape. We explore the effect of using the Bayesian learning approach for the weights on the irregular predictive landscape. For the surrogate-gradient SNNs, we also explore the ap