Training a Subsampling Mechanism in Expectation

Colin Raffel, Dieterich Lawson

Feb 17, 2017 (modified: Apr 08, 2017) ICLR 2017 workshop submission readers: everyone
  • Abstract: We describe a mechanism for subsampling sequences and show how to compute its expected output so that it can be trained with standard backpropagation. We test this approach on a simple toy problem and discuss its shortcomings.
  • TL;DR: We describe a mechanism for subsampling sequences which can be trained in expectation with standard backpropagation.
  • Conflicts: google.com
  • Keywords: Theory, Deep learning, Structured prediction

Loading