Scholarlink

In this paper, we present a novel supervised learning algorithm for neural network training based on QR decomposition with Householder reflections. The core of our study outlines the fundamental mathematical principles underlying this approach. To validate its effectiveness and robustness, we provide a detailed analysis of benchmark experiments, demonstrating the advantages of our method.

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

Neural Network Training Through Matrix Factorization

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jarosław Bilski,
  • Bartosz Kowalczyk,
  • Martyna Kukułka

摘要

In this paper, we present a novel supervised learning algorithm for neural network training based on QR decomposition with Householder reflections. The core of our study outlines the fundamental mathematical principles underlying this approach. To validate its effectiveness and robustness, we provide a detailed analysis of benchmark experiments, demonstrating the advantages of our method.