Low-Complexity OFDM Deep Neural Receivers

TL;DR

This paper introduces a low-complexity deep neural network architecture for OFDM signal decoding, utilizing a novel ResNet design with small kernels and dilation to reduce computational cost and enhance training convergence.

Contribution

A new ResNet-based OFDM neural receiver design that significantly reduces FLOPs and improves training convergence compared to existing architectures.

Findings

Reduces the number of FLOPs (NFLOPs) in OFDM neural receivers.

Improves training convergence speed.

Enhances decoding accuracy in simulations.

Abstract

Deep neural receivers (NeuralRxs) for Orthogonal Frequency Division Multiplexing (OFDM) signals are proposed for enhanced decoding performance compared to their signal-processing based counterparts. However, the existing architectures ignore the required number of epochs for training convergence and floating-point operations (FLOPs), which increase significantly with improving performance. To tackle these challenges, we propose a new residual network (ResNet) block design for OFDM NeuralRx. Specifically, we leverage small kernel sizes and dilation rates to lower the number of FLOPs (NFLOPs) and uniform channel sizes to reduce the memory access cost (MAC). The ResNet block is designed with novel channel split and shuffle blocks, element-wise additions are removed, with Gaussian error linear unit (GELU) activations. Extensive simulations show that our proposed NeuralRx reduces NFLOPs and improves training convergence while improving the decoding accuracy.