2000 character limit reached
Training a Subsampling Mechanism in Expectation
Published 22 Feb 2017 in cs.LG | (1702.06914v3)
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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
