Learning High-Quality Latent Representations for Anomaly Detection and Signal Integrity Enhancement in High-Speed Signals

TL;DR

This paper proposes a joint autoencoder-classifier framework to learn distinctive latent representations, significantly improving anomaly detection and signal integrity in high-speed memory signals, validated through multiple experiments.

Contribution

It introduces a novel joint training method that enhances latent representations for anomaly detection and signal integrity in high-speed signals.

Findings

Outperforms baseline anomaly detection methods

Improves signal integrity by an average of 11.3%

Validated across three anomaly detection algorithms

Abstract

This paper addresses the dual challenge of improving anomaly detection and signal integrity in high-speed dynamic random access memory signals. To achieve this, we propose a joint training framework that integrates an autoencoder with a classifier to learn more distinctive latent representations by focusing on valid data features. Our approach is evaluated across three anomaly detection algorithms and consistently outperforms two baseline methods. Detailed ablation studies further support these findings. Furthermore, we introduce a signal integrity enhancement algorithm that improves signal integrity by an average of 11.3%. The source code and data used in this study are available at https://github.com/Usama1002/learning-latent-representations.