Learning High-Quality Latent Representations for Anomaly Detection and Signal Integrity Enhancement in High-Speed Signals
This work addresses anomaly detection and signal integrity issues in high-speed DRAM signals, which is an incremental improvement for hardware and signal processing domains.
The paper tackles the dual challenge of anomaly detection and signal integrity enhancement in high-speed DRAM signals by proposing a joint training framework integrating an autoencoder with a classifier, which consistently outperforms baseline methods across three anomaly detection algorithms and improves signal integrity by an average of 11.3%.
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.