ARTIFICIAL INTELLIGENCE (AI) ARCHITECTURES FOR CONTINUOUS LEARNING FROM OBSERVATION, EXPERIMENTATION, CONVERSATION AND DEMONSTRATION
Abstract
There have been significant advances in the component parts of intelligence such as vision, speech, and learning, but we have not seen comparable progress on how to design an AI architecture that integrates these component parts into an intelligent set of agents that continuously improve their performance. This work will study various architectures for different classes of AI performance.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 12, 2021
- Source ID
- FA95502010118
Entities
People
- Tom M. Mitchell
Organizations
- Air Force Office of Scientific Research
- Carnegie Mellon University
- United States Air Force