For Edge AI applications, deploying online learning and adaptation on resource-constrained embedded devices can deal with fast sensor-generated streams of data in changing environments. However, since maintaining low-latency and power-efficient inference is paramount at the Edge, online learning and adaptation on the device should impose minimal additional overhead for inference. With this goal in mind, we explore energy-efficient learning and adaptation on-device for streaming-data Edge AI applications using Spiking Neural Networks (SNNs), which follow the principles of brain-inspired computing, such as high-parallelism, neuron co-located memory and compute, and event-driven processing. We propose EON-1, a brain-inspired processor for near-sensor extreme edge online feature extraction, that integrates a fast online learning and adaptation algorithm. We report results of only 1% energy overhead for learning, by far the lowest overhead when compared to other SoTA solutions, while attaining comparable inference accuracy. Furthermore, we demonstrate that EON-1 is up for the challenge of low-latency processing of HD and UHD streaming video in real-time, with learning enabled.
@article{arxiv.2406.17285,
title = {EON-1: A Brain-Inspired Processor for Near-Sensor Extreme Edge Online Feature Extraction},
author = {Alexandra Dobrita and Amirreza Yousefzadeh and Simon Thorpe and Kanishkan Vadivel and Paul Detterer and Guangzhi Tang and Gert-Jan van Schaik and Mario Konijnenburg and Anteneh Gebregiorgis and Said Hamdioui and Manolis Sifalakis},
journal= {arXiv preprint arXiv:2406.17285},
year = {2024}
}