EON-1: A Brain-Inspired Processor for Near-Sensor Extreme Edge Online Feature Extraction

TL;DR

EON-1 is a brain-inspired processor designed for near-sensor online feature extraction in edge AI, achieving low energy overhead and real-time processing of high-definition video streams.

Contribution

The paper introduces EON-1, a novel brain-inspired processor with an integrated fast online learning algorithm for energy-efficient, real-time edge AI applications.

Findings

Only 1% energy overhead for online learning.

Achieves real-time processing of HD and UHD video streams.

Comparable inference accuracy to state-of-the-art methods.

Abstract

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.