Neural network (NN)-based receivers for orthogonal frequency division multiplex (OFDM) excel through promising performance and benefits in their applicability. In this paper we analyze their capabilities when they are imposed with practical constraints that have to be considered when implementing such a receiver on hardware. Specifically, we focus on the effects of uniform linear affine quantization and it is shown which performance can be achieved by utilizing quantization-aware training (QAT) with trainable quantizers. In order to reduce the computational complexity of the NN-based receiver different pruning methods are investigated. We showcase that a reduction of the number of floating-point operations (FLOPs) by more than 50% is possible at the cost of less than 0.25 dB difference. Finally, an intuition on joint pruning and quantization is given.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    On the Implementation of Neural Network-based OFDM Receivers




    Publication date :

    2024-06-24


    Size :

    350419 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Comparison of Correlation-Based OFDM Radar Receivers

    Mercier, Steven / Bidon, Stephanie / Roque, Damien et al. | IEEE | 2020


    Iterative MRC and EGC Receivers for MIMO-OFDM Systems

    Pereira, Andreia / Bento, Pedro / Gomes, Marco et al. | IEEE | 2018


    Orthogonal Neural Network Based Predistortion for OFDM Systems

    Rodriguez, Nibaldo / Cubillos, Claudio | IEEE | 2007


    Optical FET receivers for neural network applications [2400-39]

    Luo, J. / Grot, A. / Psaltis, D. et al. | British Library Conference Proceedings | 1995


    A Novel Precoder Design for OFDM Receivers in Unknown Fading Channels

    Hasegawa, Fumihiro / Plataniotis, Konstantiotis. N. / Pasupathy, Subbarayan | IEEE | 2008