Timezone: »

 
Poster
Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks
Frank Schneider · Felix Dangel · Philipp Hennig

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

When engineers train deep learning models, they are very much "flying blind". Commonly used methods for real-time training diagnostics, such as monitoring the train/test loss, are limited. Assessing a network's training process solely through these performance indicators is akin to debugging software without access to internal states through a debugger. To address this, we present Cockpit, a collection of instruments that enable a closer look into the inner workings of a learning machine, and a more informative and meaningful status report for practitioners. It facilitates the identification of learning phases and failure modes, like ill-chosen hyperparameters. These instruments leverage novel higher-order information about the gradient distribution and curvature, which has only recently become efficiently accessible. We believe that such a debugging tool, which we open-source for PyTorch, is a valuable help in troubleshooting the training process. By revealing new insights, it also more generally contributes to explainability and interpretability of deep nets.

Keywords: Deep Learning · Optimization · Interpretability

Author Information

Frank Schneider (University of Tübingen)
Felix Dangel (University of Tübingen)
Philipp Hennig (University of Tübingen and MPI Tübingen)

More from the Same Authors