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.
Highlights
Since the early 2010s, computer vision has been dominated by the introduction of convolutional neural networks (CNNs), which have yielded unprecedented success in previously challenging tasks such as image recognition, image segmentation or object detection, among others
While we demonstrate the benefit of optimizing based on energy consumption, we believe this strategy is extendable to any approach that uses backpropagation to train the network, be it through a spiking network or a non-spiking network
The synaptic operations (SynOps) Loss Term Leads to a Reduction in Network Activity on Dynamic Vision Sensor (DVS) Data In Figure 2, we show the results of four methods to reduce the activity of the network, in a way that yields energy savings
Summary
Since the early 2010s, computer vision has been dominated by the introduction of convolutional neural networks (CNNs), which have yielded unprecedented success in previously challenging tasks such as image recognition, image segmentation or object detection, among others. Considering the theory of neural networks was mostly developed decades earlier, one of the main driving factors behind this evolution was the widespread availability of high-performance computing devices and general purpose Graphic Processing Units (GPU). In parallel with the increase in computational requirements (Strubell et al, 2019), the last decades have seen a considerable development of portable, miniaturized, battery-powered devices, which pose constraints on the maximum power consumption. Attempts at reducing the power consumption of traditional deep learning models have been made. These involve optimizing the network architecture, in order to find more compact networks (with fewer layers, or fewer neurons per layer) that perform well as larger networks. Other work looks for more efficient network structures through a full-fledged architecture search (Cai et al, 2018). The latter work was one of the winners of the Google “Visual Wake Words Challenge” at CVPR 2019, which sought models with memory usage under 250 kB, model size under 250 kB and per-inference multiply-add count (MAC) under 60 millions
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
