NeuralEQ: Neural-Network-Based Equalizer for High-Speed Wireline Communication

TL;DR

NeuralEQ is a neural network-based equalizer designed for high-speed wireline communication, outperforming traditional methods like FFE and DFE by mimicking the forward-backward algorithm with reduced complexity, verified through real channel simulations.

Contribution

The paper introduces NeuralEQ, a novel neural network equalizer that effectively replicates the forward-backward algorithm with lower complexity for wireline channels.

Findings

NeuralEQ outperforms FFE and DFE in BER performance.

NeuralEQ reduces the complexity of the forward-backward algorithm.

Performance validated through simulations with real channels.

Abstract

With the growing demand for high-bandwidth applications like video streaming and cloud services, the data transfer rates required for wireline communication keeps increasing, making the channel loss a major obstacle in achieving low bit error rate (BER). Equalization techniques such as feed-forward equalizer (FFE) and decision feedback equalizer (DFE) are commonly used to compensate for channel loss in wireline communication, but they have limitations in terms of noise boosting and timing constraints. On the other hand, the forward-backward algorithm can achieve better BER performance, but its high complexity makes it impractical for wireline communication. In this work, we propose a novel neural network, NeuralEQ, that effectively mimics the forward-backward algorithm and performs better than FFE and DFE while reducing complexity of the forward-backward algorithm. Performance of NeuralEQ is verified through simulations using real channels.