deepGenerativeModels: Difference between revisions

From statwiki
Jump to navigation Jump to search
(Created page with "== Problem == To properly train a neural network a large labeled dataset, however large datasets of labeled data are not always available. This paper covers a method of generati...")
 
Line 5: Line 5:


== Methodology==
== Methodology==
== Future Work ==
These models scale linearly in proportion to the number of classes in the data sets. The number of evaluations could be reduced by truncating the posterior mass or by using error-correcting output codes.

Revision as of 21:12, 3 November 2015

Problem

To properly train a neural network a large labeled dataset, however large datasets of labeled data are not always available. This paper covers a method of generating labeled data for neural network training.


Methodology

Future Work

These models scale linearly in proportion to the number of classes in the data sets. The number of evaluations could be reduced by truncating the posterior mass or by using error-correcting output codes.