Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Machine Learning Science and TechnologyOpen Access

Variational autoencoders for at-source data reduction and anomaly detection in high energy particle detectors

View Full Paper
Ask AI
Bookmark
Share

Authors

AYAlexander YueHJHaoyi JiaJGJ. L. Gonski

Discussion

Loading...

Member takes

Overview

Machine learning using variational autoencoders demonstrates improved data reduction and anomaly detection in high energy particle detectors, highlighting its potential for future applications.

Key Points

  • Data reduction is significantly improved using variational autoencoders, allowing efficient processing within high energy particle detectors.
  • Encoder-based data compression preserves the performance of off-detector analysis while decreasing the off-detector data rate.
  • Latent space representations from variational autoencoders serve as effective tools for real-time anomaly detection in sensor monitoring.
  • These findings motivate further exploration of autoencoder-based solutions in designing next-generation high-energy physics detectors.

Cite This Study

Yue et al. (2025) studied this question.

synapsesocial.com/papers/68c1ae6654b1d3bfb60e5fb2https://doi.org/10.1088/2632-2153/adf0c0
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Anomaly Detection using Autoencoders on Fundamental LZ Signals2025
  2. 2Anomaly Detection using Autoencoders on Fundamental LZ Signals2025
  3. 3Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment2024
  4. 4Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment2024 · 2 citations
  5. 5Data Aided Sensing with Variational Autoencoder2024 · 2 citations