Microwave diffractive neural network chips for sensing and computing
Open Access
- 18 September 2026
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (38)
Abstract
Electromagnetic diffractive neural networks (DNNs) enable ultra–low-power, low-latency artificial intelligence (AI) inference, yet optical implementations suffer from fabrication and scalability limits, and metasurface microwave systems remain bulky. We present a chip-scale microwave diffractive neural network (MDNN) fabricated in a GaAs semiconductor process, integrating cascaded couplers and phase shifters to implement a diffraction network within a millimeter-scale footprint. The MDNN chip reduces the size of conventional MDNNs by over four orders of magnitude, achieves a computational latency of 2.05 ns, and delivers a system-level energy efficiency of 0.83 TOPS/W. We demonstrate its versatility through three functional prototypes: MNIST handwritten digit recognition, multi-user interference suppression, and real-time obstacle perception for drones. These experiments achieved more than 86% accuracy, validating the capability of the MDNN chip to directly perform both digital image processing and in-situ electromagnetic information processing in the microwave domain. We hope this chip architecture opens a new pathway toward highly integrated designs for electromagnetic DNNs.Keywords
Funding Information
- National Natural Science Foundation of China (62301147, 62288101)
- China Postdoctoral Science Foundation (2021M700761, 2022T150112)
- Natural Science Foundation of Jiangsu Province (BK20230822)
- National Key Research and Development Program of China (2022YFA1404903)
- Jiangsu Joint Laboratory of Multidimensional Perceptual Information Technology (bm2022017)
- Special Fund for Key Basic Research in Jiangsu Province (BK20243015)
- Major Project of Natural Science Foundation of Jiangsu Province (BK20212002, BK20210209)
- Young Elite Scientists Sponsorship Program by CAST (2022QNRC001)
- State Key Laboratory of Millimeter Waves Southeast University China (K201924)
- Fundamental Research Funds for the Central Universities (2242023K5002, 2242018R30001, 2242022R20017)
- 111 Project (1112-05)
This publication has 32 references indexed in Scilit:
- Millimeter-wave spoof plasmonic phase shifter with customizable phase resolutionChip, 2026
- Classification of Metal Handwritten Digits Based on Microwave Diffractive Deep Neural NetworkAdvanced Optical Materials, 2023
- Reprogrammable Nonlinear Transmission Controls Using an Information MetasurfaceAdvanced Optical Materials, 2023
- Reprogrammable Spoof Plasmonic ModulatorAdvanced Functional Materials, 2023
- Dynamic recognition and mirage using neuro-metamaterialsNature Communications, 2022
- Space-efficient optical computing with an integrated chip diffractive neural networkNature Communications, 2022
- Polarization Multiplexing Hologram Realized by Anisotropic Digital MetasurfaceAdvanced Theory and Simulations, 2021
- Performing optical logic operations by a diffractive neural networkLight: Science & Applications, 2020
- Controllable and Programmable Nonreciprocity Based on Detachable Digital Coding MetasurfaceAdvanced Optical Materials, 2019
- Deep learning with coherent nanophotonic circuitsNature Photonics, 2017