LABEL-EFFICIENT ACTIVE RESILIENT NETWORKS (LEARN)
Abstract
The goal of this program is to the process of training machine learning models more efficient by reducing the amount of labeled data required to build a model by six or more orders of magnitude, and by reducing the amount of data needed to adapt models to new environments to tens to hundreds of labeled examples.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Sep 25, 2019
- Source ID
- FA87501910504
Entities
People
- Trevor Darrell
Organizations
- Defense Advanced Research Projects Agency
- Rome Laboratory
- University of California Regents