A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Network. (arXiv:2103.00944v3 [cs.CV] UPDATED)

Spiking neural networks (SNNs) offer an inherent ability to process
spatial-temporal data, or in other words, realworld sensory data, but suffer
from the difficulty of training high accuracy models. A major thread of
research on SNNs is on converting a pre-trained convolutional neural network
(CNN) to an SNN of the same structure. State-of-the-art conversion methods are
approaching the accuracy limit, i.e., the near-zero accuracy loss of SNN
against the original CNN. However, we note that this is made possible only …

arxiv convolutional neural network cv energy network neural network spiking neural network