Training a Subsampling Mechanism in Expectation

22 Feb 2017  ·  Colin Raffel, Dieterich Lawson ·

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.

PDF Abstract

Tasks
Add Remove

Datasets

  Add Datasets introduced or used in this paper

Results from the Paper
Add Remove

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy