Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications

Martino Sorbaro; Qian Liu; Massimo Bortone; Sadique Sheik

doi:10.3389/fnins.2020.00662

Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications

Front Neurosci. 2020 Jun 30:14:662. doi: 10.3389/fnins.2020.00662. eCollection 2020.

Authors

Martino Sorbaro^{1

2}, Qian Liu¹, Massimo Bortone¹, Sadique Sheik¹

Affiliations

¹ SynSense (formerly aiCTX), Zurich, Switzerland.
² Institute of Neuroinformatics, University of Zürich and ETH Zürich, Zurich, Switzerland.

Abstract

In the last few years, spiking neural networks (SNNs) have been demonstrated to perform on par with regular convolutional neural networks. Several works have proposed methods to convert a pre-trained CNN to a Spiking CNN without a significant sacrifice of performance. We demonstrate first that quantization-aware training of CNNs leads to better accuracy in SNNs. One of the benefits of converting CNNs to spiking CNNs is to leverage the sparse computation of SNNs and consequently perform equivalent computation at a lower energy consumption. Here we propose an optimization strategy to train efficient spiking networks with lower energy consumption, while maintaining similar accuracy levels. We demonstrate results on the MNIST-DVS and CIFAR-10 datasets.

Keywords: CIFAR10; MNIST-DVS; convolutional networks; energy consumption; loss function; neuromorphic computing; spiking networks; synaptic operations.