Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks. (arXiv:2211.08410v1 [cs.NE])

Spiking neural networks (SNNs) are well suited for resource-constrained
applications as they do not need expensive multipliers. In a typical
rate-encoded SNN, a series of binary spikes within a globally fixed time window
is used to fire the neurons. The maximum number of spikes in this time window
is also the latency of the network in performing a single inference, as well as
determines the overall energy efficiency of the model. The aim of this paper is
to reduce this …

artificial arxiv conversion latency low network networks neural network neural networks rate spiking neural networks