Learned Integrated Sensing Pipeline: Reconfigurable Metasurface Transceivers as Trainable Physical Layer in an Artificial Neural Network. Issue 3 (6th December 2019)

• Record Type: Journal Article
• Authors: del Hougne, Philipp; Imani, Mohammadreza F.; Diebold, Aaron V.; Horstmeyer, Roarke; Smith, David R.
• Is Part Of: Advanced science. Volume 7:Issue 3(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-12-06
• Subjects: machine learning -- metasurfaces -- sensing -- wavefront shaping; Science -- Periodicals; 505
• DOI: 10.1002/advs.201901913
• Languages: English
• ISSNs: 2198-3844

Abstract

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. Abstract : Optimal wavefronts to probe a scene with microwave radiation in order to recognize objects therein are learned by integrating a model of the sensor's reconfigurable physical layer into the machine‐learning pipeline used to process the measurements. Thereby the amount of task‐relevant information obtained per measurement is maximized, enabling sensing with low latency and computational burden.