An Active Archicture for Self-Learning
Abstract
Create a novel architecture that extracts events from the flow of time in an unsupervised manner and substitutes the conventional classifier by an external memory system that stores and organizes the extracted events to foster continuous growth in the memory store and continuous improvement of performance.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jul 15, 2019
- Source ID
- FA94531810039
Entities
People
- José PrÃncipe
Organizations
- Air Force Research Laboratory
- Defense Advanced Research Projects Agency
- University of Florida