Skip to yearly menu bar Skip to main content


Poster

Deciding How to Decide: Dynamic Routing in Artificial Neural Networks

Mason McGill · Pietro Perona

Gallery #116

Abstract:

We propose and systematically evaluate three strategies for training dynamically-routed artificial neural networks: graphs of learned transformations through which different input signals may take different paths. Though some approaches have advantages over others, the resulting networks are often qualitatively similar. We find that, in dynamically-routed networks trained to classify images, layers and branches become specialized to process distinct categories of images. Additionally, given a fixed computational budget, dynamically-routed networks tend to perform better than comparable statically-routed networks.

Live content is unavailable. Log in and register to view live content