Figure 5.

Spiking Neural Networks equipped with eRBP with stochastic synapses (multiplicative noise) achieve SynOp-MAC parity at the MNIST task. The number of multiply-accumulate (MAC) operations required for reaching a given accuracy is compared to the number of synaptic operations (SynOps) in the spiking network for the MNIST learning task (784-200-200-10 network). Both networks requires roughly the same number of operations to reach the same accuracy during learning. Only MACs incurred in the matrix multiplications are taken into account (other necessary operations e.g., additions, logistic function calls, and weight updates were not taken into account here, and would further favor the spiking network).