Topic: slow tangent modes

Spiking neural networks (SNNs) promise energy efficiency and offer a more brain-like alternative to artificial neural networks. However, training them on challenging tasks requiring credit assignment across long time horizons remains a significant challenge due to their discrete spiking interactions, which make the error landscape non-differentiable. A recent approach replaces the spike interactions with a surrogate gradient in the backward pass of gradient descent.\footnote{Neftci et al., \textit{Surrogate Gradient Learning in Spiking Neural Networks}, IEEE Signal Processing Magazine, 2019}\f