Powering AI at the edge: A robust, memristor-based binarized neural network with near-memory computing and miniaturized solar cell

• Published in: Nature communications Vol. 15; no. 1; p. 741
• Main Authors: Jebali, Fadi, Majumdar, Atreya, Turck, Clément, Harabi, Kamel-Eddine, Faye, Mathieu-Coumba, Muhr, Eloi, Walder, Jean-Pierre, Bilousov, Oleksandr, Michaud, Amadéo, Vianello, Elisa, Hirtzlin, Tifenn, Andrieu, François, Bocquet, Marc, Collin, Stéphane, Querlioz, Damien, Portal, Jean-Michel
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 25.01.2024; Nature Portfolio
• Subjects: Accuracy; Amplifier design; Artificial intelligence; Circuits; Computation; Computer memory; Electronics; Energy efficiency; Energy harvesting; Engineering Sciences; Environmental monitoring; Illumination; Image classification; Memristors; Neural networks; Photovoltaic cells; Power supply; Robustness; Sense amplifiers; Solar cells; Electrical and electronic engineering; Electronic devices
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-024-44766-6

Memristor-based neural networks provide an exceptional energy-efficient platform for artificial intelligence (AI), presenting the possibility of self-powered operation when paired with energy harvesters. However, most memristor-based networks rely on analog in-memory computing, necessitating a stable and precise power supply, which is incompatible with the inherently unstable and unreliable energy harvesters. In this work, we fabricated a robust binarized neural network comprising 32,768 memristors, powered by a miniature wide-bandgap solar cell optimized for edge applications. Our circuit employs a resilient digital near-memory computing approach, featuring complementarily programmed memristors and logic-in-sense-amplifier. This design eliminates the need for compensation or calibration, operating effectively under diverse conditions. Under high illumination, the circuit achieves inference performance comparable to that of a lab bench power supply. In low illumination scenarios, it remains functional with slightly reduced accuracy, seamlessly transitioning to an approximate computing mode. Through image classification neural network simulations, we demonstrate that misclassified images under low illumination are primarily difficult-to-classify cases. Our approach lays the groundwork for self-powered AI and the creation of intelligent sensors for various applications in health, safety, and environment monitoring.