Scholarlink

Abstract <p>We propose using the latent space (LS) of an autoencoder (AE) as a compressed representation of input data in gamma astronomy. The AE learns compressed representations directly from data and its LS dimensionality <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(N\)</EquationSource> <!--PhysPart2670078Dubenskaya-m1--> </InlineEquation> is tunable, enabling optimization for specific tasks. To ensure interpretability and control, we train two dedicated networks: one maps the LS to physical parameters, while the other performs the inverse mapping. The approach was validated on TAIGA-HiSCORE simulated data, demonstrating promising results.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Interpreting and Controlling Latent Space Parameters of Autoencoders for TAIGA-HiSCORE Data

  • 期刊论文

  • 发表日期：

    2026年7月20日

查看全文
  • Yu. Dubenskaya,
  • S. Polyakov,
  • A. Kryukov,
  • A. Demichev,
  • P. Volchugov,
  • E. Gres,
  • D. Zhurov,
  • E. Postnikov,
  • A. Razumov

摘要

Abstract

We propose using the latent space (LS) of an autoencoder (AE) as a compressed representation of input data in gamma astronomy. The AE learns compressed representations directly from data and its LS dimensionality \(N\) is tunable, enabling optimization for specific tasks. To ensure interpretability and control, we train two dedicated networks: one maps the LS to physical parameters, while the other performs the inverse mapping. The approach was validated on TAIGA-HiSCORE simulated data, demonstrating promising results.