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

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.

Radiative transfer model for contaminated rough slabs.

We present a semi-analytical model to simulate the bidirectional reflectance distribution function (BRDF) of a rough slab layer containing impurities. This model has been optimized for fast computation in order to analyze massive hyperspectral data by a Bayesian approach. We designed it for planetary surface ice studies but it could be used for other purposes. It estimates the bidirectional reflectance of a rough slab of material containing inclusions, overlaying an optically thick media (semi-infinite media or stratified media, for instance granular material). The inclusions are assumed to be close to spherical and constituted of any type of material other than the ice matrix. It can be any other type of ice, mineral, or even bubbles defined by their optical constants. We assume a low roughness and we consider the geometrical optics conditions. This model is thus applicable for inclusions larger than the considered wavelength. The scattering on the inclusions is assumed to be isotropic. This model has a fast computation implementation and thus is suitable for high-resolution hyperspectral data analysis.