Interactive learning with a “society of models”

Digital library access is driven by features, but the relevance of a feature for a query is not always obvious. This paper describes an approach for integrating a large number of context-dependent features into a semi-automated tool. Instead of requiring universal similarity measures or manual selec...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition 1997-04, Vol.30 (4), p.565-581
Main Authors: Minka, T.P., Picard, R.W.
Format: Article
Language:English
Subjects:
Annotation
Image and video databases
Learning
Multiple models
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Digital library access is driven by features, but the relevance of a feature for a query is not always obvious. This paper describes an approach for integrating a large number of context-dependent features into a semi-automated tool. Instead of requiring universal similarity measures or manual selection of relevant features, the approach provides a learning algorithm for selecting and combining groupings of the data, where groupings can be induced by highly specialized features. The selection process is guided by positive and negative examples from the user. The inherent combinatorics of using multiple features is reduced by a multistage grouping generation, weighting, and collection process. The stages closest to the user are trained fastest and slowly propagate their adaptations back to earlier stages, improving overall performance.
ISSN:0031-3203
1873-5142
DOI:10.1016/S0031-3203(96)00113-6