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.
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: