TitleAnalysis of the IJCNN 2011 UTL Challenge
Publication TypeJournal Article
Year of Publication2012
AuthorsGuyon, I, Dror, G, Lemaire, V, Silver, DL, Taylor, G, Aha, DW
JournalNeural Networks
Volume32
Pagination174-178
Keywordscompetition, deep learning, Transfer learning
Abstract

We organized a challenge in ‘‘Unsupervised and Transfer Learning’’: the UTL challenge (http://
clopinet.com/ul). We made available large datasets from various application domains: handwriting
recognition, image recognition, video processing, text processing, and ecology. The goal was to learn data
representations that capture regularities of an input space for re-use across tasks. The representations
were evaluated on supervised learning ‘‘target tasks’’ unknown to the participants. The first phase of the
challenge was dedicated to ‘‘unsupervised transfer learning’’ (the competitors were given only unlabeled
data). The second phase was dedicated to ‘‘cross-task transfer learning’’ (the competitors were provided
with a limited amount of labeled data from ‘‘source tasks’’, distinct from the ‘‘target tasks’’). The analysis
indicates that learned data representations yield significantly better results than those obtained with
original data or data preprocessed with standard normalizations and functional transforms.

URLhttp://dx.doi.org/10.1016/j.neunet.2012.02.010
Refereed DesignationRefereed
Full Text
pdf: 
http://www.nrl.navy.mil/itd/aic/sites/www.nrl.navy.mil.itd.aic/files/pdfs/%28Guyon%20et%20al.%2C%202012%20NNj%29%20Analysis%20of%20the%20IJCNN%202011%20UTL%20Challenge%20%28Final%20Version%29.pdf
NRL Publication Release Number: 
11-1226-0788
pub_tags: 
machine learning
transfer learning
deep learning
competition
key_pub_tags: