Long Short-Term Memory Neuron Equalizer

TL;DR

This paper introduces a neuromorphic hardware-based LSTM neural network equalizer for signal recovery, demonstrating its adaptability and superior performance over traditional methods through FPGA implementation.

Contribution

It presents a novel trainable LSTM neural network equalizer compatible with multiple signal types, outperforming benchmark approaches in digital and analog neuromorphic hardware implementations.

Findings

Outperforms traditional equalizers in multiple metrics

Compatible with both analog and digital neuromorphic hardware

Effective for various frequency signal equalization

Abstract

In this work we propose a neuromorphic hardware based signal equalizer by based on the deep learning implementation. The proposed neural equalizer is plasticity trainable equalizer which is different from traditional model designed based DFE. A trainable Long Short-Term memory neural network based DFE architecture is proposed for signal recovering and digital implementation is evaluated through FPGA implementation. Constructing with modelling based equalization methods, the proposed approach is compatible to multiple frequency signal equalization instead of single type signal equalization. We shows quantitatively that the neuronmorphic equalizer which is amenable both analog and digital implementation outperforms in different metrics in comparison with benchmarks approaches. The proposed method is adaptable both for general neuromorphic computing or ASIC instruments.