IM-Loss: Information Maximization Loss for Spiking Neural Networks

The conditional entropy H(O|U) can be expressed as the below equation according to the Eq.5 and Eq.7. I(U;O) = H(O) (10) A.2 Algorithm The proposed training algorithm of an SNN is presented in Algo.1. Algorithm 1 The proposed training algorithm of an SNN. Input: Initialized SNN; training dataset; total training epochs, I; training iterations per epoch, J. Output: The trained SNN. W, where η is learning rate.