Generalization Bounds of Spiking Neural Networks via Rademacher Complexity

ArXi:2605.02927v1 Announce Type: cross Spiking Neural Networks (SNNs) have garnered increasing attention as one of bio-inspired models due to their great potential in neuromorphic computing and sparse computation. Many practical algorithms and techniques have been developed; however, theoretical understandings of the generalization, that is, the extent to which SNNs perform well on unseen data, are far from clear.