Making a Differentiable ANN-SNN Continuum using Spiking Threshold Gating Cells

Spiking neural networks (SNNs), inspired by the brain and motivated by the potential for energy efficiency, replace real-valued activations with spikes generated by stateful neurons, but the discontinuity of spike generation complicates gradient-based training. Building on Threshold Gating (TG), which expresses neural nonlinearities as affine branches selected by sigmoid gates with tunable sharpness, we introduce Spiking Threshold Gating ($\mathrm{STG}$), a parameterized cell enabling a differentiable transition from stateless ANN activations to stateful spiking neurons. Unlike prior ANN-to-SNN conversion methods, $\mathrm{STG}$ allows ANN pretraining and subsequent hardening within the same cell, using exact gradients of the smooth cell during training rather than surrogate gradients. We then introduce a curriculum that progressively sharpens the cell’s gates during training, achieving state-of-the-art results on several event-based datasets. We additionally propose a novel input-routed parameterization that separates membrane-driven firing from input-dependent event payloads, further improving performance through flexible, multi-branch emissions.