NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Salience Assignment for Multiple-Instance RegressionWe present a Multiple-Instance Learning (MIL) algorithm for determining the salience of each item in each bag with respect to the bag's real-valued label. We use an alternating-projections constrained optimization approach to simultaneously learn a regression model and estimate all salience values. We evaluate this algorithm on a significant real-world problem, crop yield modeling, and demonstrate that it provides more extensive, intuitive, and stable salience models than Primary-Instance Regression, which selects a single relevant item from each bag.
Document ID
20090028740
Acquisition Source
Jet Propulsion Laboratory
Document Type
Preprint (Draft being sent to journal)
External Source(s)
Authors
Wagstaff, Kiri L.
(Jet Propulsion Lab., California Inst. of Tech. Pasadena, CA, United States)
Lane, Terran
(New Mexico Univ. Albuquerque, NM, United States)
Date Acquired
August 24, 2013
Publication Date
June 24, 2007
Subject Category
Statistics And Probability
Meeting Information
Meeting: ICML 2007 Workshop on Constrained Optimization and Structured Output Spaces
Location: Covallis, OR
Country: United States
Start Date: June 24, 2007
Sponsors: Oregon State Univ.
Funding Number(s)
CONTRACT_GRANT: 1R01MH076282-01
Distribution Limits
Public
Copyright
Other
Keywords
regression
crop yield prediction
relevance

Available Downloads

There are no available downloads for this record.
No Preview Available