Understanding intermediate layers using linear classifier probes

Guillaume Alain, Yoshua Bengio

Feb 17, 2017 (modified: Feb 17, 2017) ICLR 2017 workshop submission readers: everyone
  • Abstract: Neural network models have a reputation for being black boxes. We propose a new method to better understand the roles and dynamics of the intermediate layers. Our method uses linear classifiers, referred to as "probes", where a probe can only use the hidden units of a given intermediate layer as discriminating features. Moreover, these probes cannot affect the training phase of a model, and they are generally added after training. We demonstrate how this can be used to develop a better intuition about models and to diagnose potential problems.
  • TL;DR: Investigating deep learning models by proposing a different concept of information
  • Keywords: Deep learning, Supervised Learning, Theory
  • Conflicts: umontreal.ca, google.com