Pfahler/Morik/2021a: Explaining Deep Learning Representations by Tracing the Training Process

Bibtype Misc
Bibkey Pfahler/Morik/2021a
Author Pfahler, Lukas and Morik, Katharina
Ls8autor Morik, Katharina
Pfahler, Lukas
Title Explaining Deep Learning Representations by Tracing the Training Process
Abstract We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a) find the most influential training examples during training and b) analyze which classes attributed most to the final representation. Our method is general: it can be wrapped around any iterative optimization procedure and covers a variety of neural network architectures, including feed-forward networks and convolutional neural networks. We first propose a method for stochastic training with single training instances, but continue to also derive a variant for the common mini-batch training. In experimental evaluations, we show that our method identifies highly representative training instances that can be used as an explanation. Additionally, we propose a visualization that provides explanations in the form of aggregated statistics over the whole training process.
Month 09
Year 2021
Url https://arxiv.org/pdf/2109.05880.pdf

  • Privacy Policy
  • Imprint