Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Universum Prescription: Regularization Using Unlabeled Data release_qbg62yftnvfk5ctkubl6zj7hni

by Xiang Zhang, Yann LeCun

Abstract

This paper shows that simply prescribing "none of the above" labels to unlabeled data has a beneficial regularization effect to supervised learning. We call it universum prescription by the fact that the prescribed labels cannot be one of the supervised labels. In spite of its simplicity, universum prescription obtained competitive results in training deep convolutional networks for CIFAR-10, CIFAR-100, STL-10 and ImageNet datasets. A qualitative justification of these approaches using Rademacher complexity is presented. The effect of a regularization parameter — probability of sampling from unlabeled data — is also studied empirically.
In application/xml+jats format

Archived Files and Locations

application/pdf  700.2 kB
file_5abroojmajf3dgwisgcbscyfj4
ojs.aaai.org (publisher)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2017-02-13
Proceedings Metadata
Not in DOAJ
Not in Keepers Registry
ISSN-L:  2159-5399
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d89e968f-9fbb-4025-b5d3-264caa7b1ed2
API URL: JSON