This paper introduces a novel over-the-air computation method that utilizes low-complexity transmissive intelligent surfaces (TISs) for neural network inference. It is demonstrated that the signal propagation model through TIS closely resembles the fully connected layer of neural networks. And through training, the TIS phase shifts can be determined to perform a specific computation on radio-frequency (RF) signals. Considering the practical constraints of TIS designs with continuous phase shifts in millimeter-wave (mmWave) frequency, we propose a novel discretized complex-valued neural network structure and a training method suitable for low-complexity 1-bit and 2-bit TIS-based neural network layers. It is shown through simulation that the proposed method achieves high accuracy on an image classification task even for 1-bit or 2-bit TISs.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Radio-Frequency-Based Fully Connected Layer using 1-Bit and 2-Bit Transmissive Intelligent Surfaces


    Contributors:


    Publication date :

    2024-10-07


    Size :

    1794279 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Radio-Frequency-Based 2-D Convolutional Layer using Transmissive Intelligent Surfaces

    Zhang, Jingyuan / Chen, Haige / Blough, Douglas M. | IEEE | 2024


    Low-Complexity DoA Estimation using Transmissive Intelligent Surfaces

    Zhang, Jingyuan / Tai, Ching-Lun / Sivakumar, Raghupathy et al. | IEEE | 2024


    RADIO WAVE-TRANSMISSIVE COVER

    TSUBOI TOMOKATSU | European Patent Office | 2018

    Free access


    RADIO WAVE TRANSMISSIVE COVER AND METHOD FOR SETTING PLATE THICKNESS OF RADIO WAVE TRANSMISSIVE COVER

    TOKUNAGA SEIYA / MAEDA HIDETO / ISOBE KENJI et al. | European Patent Office | 2018

    Free access