Scholarlink

This paper introduces a simplified version of the BBATDD algorithm (Boosting-Based Algorithm Trained with Drift Detector), called A-BBATDD, which aims to speed up neural network training. Instead of updating the importance of each training example individually, the new version uses an approximation based on the whole mini-batches. This makes the method easier to use with standard machine learning tools such as TensorFlow or PyTorch. The algorithm still focuses on sampling the most difficult examples for the network and includes a drift detection mechanism (CUSUM) to reset the importance values when the network performance changes significantly. Experiments on the MNIST dataset show that the performance of the method is especially sensitive to the mini-batch size.

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

Approximate Importance-Based Sampling for Neural Network Training

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Piotr Duda,
  • Mateusz Wojtulewicz,
  • Leszek Rutkowski

摘要

This paper introduces a simplified version of the BBATDD algorithm (Boosting-Based Algorithm Trained with Drift Detector), called A-BBATDD, which aims to speed up neural network training. Instead of updating the importance of each training example individually, the new version uses an approximation based on the whole mini-batches. This makes the method easier to use with standard machine learning tools such as TensorFlow or PyTorch. The algorithm still focuses on sampling the most difficult examples for the network and includes a drift detection mechanism (CUSUM) to reset the importance values when the network performance changes significantly. Experiments on the MNIST dataset show that the performance of the method is especially sensitive to the mini-batch size.