Learned Integrated Sensing Pipeline: Reconfigurable Metasurface Transceivers as Trainable Physical Layer in an Artificial Neural Network

Advanced Science

Roarke Horstmeyer¹  Aaron V. Diebold²  David R. Smith²  Mohammadreza F. Imani²  Philipp delHougne³ 

[1] Biomedical Engineering Department Duke University Durham NC 27708 USA;Center for Metamaterials and Integrated Plasmonics Department of Electrical and Computer Engineering Duke University Durham NC 27708 USA;Institut de Physique de Nice CNRS UMR 7010 Université Côte d'Azur Nice 06108 France;

关键词: machine learning;    metasurfaces;    sensing;    wavefront shaping;   

DOI  :  10.1002/advs.201901913

来源: DOAJ

【 摘 要 】

Abstract The rapid proliferation of intelligent systems (e.g., fully autonomous vehicles) in today's society relies on sensors with low latency and computational effort. Yet current sensing systems ignore most available a priori knowledge, notably in the design of the hardware level, such that they fail to extract as much task‐relevant information per measurement as possible. Here, a “learned integrated sensing pipeline” (LISP), including in an end‐to‐end fashion both physical and processing layers, is shown to enable joint learning of optimal measurement strategies and a matching processing algorithm, making use of a priori knowledge on task, scene, and measurement constraints. Numerical results demonstrate accuracy improvements around 15% for object recognition tasks with limited numbers of measurements, using dynamic metasurface apertures capable of transceiving programmable microwave patterns. Moreover, it is concluded that the optimal learned microwave patterns are nonintuitive, underlining the importance of the LISP paradigm in current sensorization trends.

【 授权许可】

Unknown