tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networks. (arXiv:2206.08656v1 [cs.NE])

Web: http://arxiv.org/abs/2206.08656

Larger Spiking Neural Network (SNN) models are typically favorable as they
can offer higher accuracy. However, employing such models on the resource- and
energy-constrained embedded platforms is inefficient. Towards this, we present
a tinySNN framework that optimizes the memory and energy requirements of SNN
processing in both the training and inference phases, while keeping the
accuracy high. It is achieved by reducing the SNN operations, improving the
learning quality, quantizing the SNN parameters, and selecting the appropriate
SNN model. Furthermore, …

arxiv energy memory networks neural neural networks spiking neural networks