Supplementary Materials for: Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State

Figure 1 illustrates our feedback models with single-layer and multi-layer structure as indicated in Sections 4.1 and 4.3. We present the pseudocode of one iteration of IDE training in Algorithm 1 to better illustrate our training method. Input: Network parameters θ; Input data x; Label y; Time steps T; Other hyperparameters; Output: Trained network parameters θ. Simulate the SNN by T time steps with input x based on Eq. (2) and calculate the final (weighted) average firing rate a[T ]; Calculate the output o and the loss L based on o and y. Update θ based on the gradient-based optimizer.