Accession Number:

ADA556704

Title:

Analysis Of The IJCNN 2011 UTL Challenge

Descriptive Note:

Journal article preprint

Corporate Author:

NAVAL RESEARCH LAB WASHINGTON DC

Report Date:

2012-01-13

Pagination or Media Count:

13.0

Abstract:

We organized a challenge in Unsupervised and Transfer Learning the UTL challenge. 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.

Subject Categories:

  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE