Training a Subsampling Mechanism in ExpectationDownload PDF

11 Dec 2024 (modified: 08 Apr 2017)ICLR 2017Readers: 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
6 Replies

Loading