You are here

Probabilistic and Relational Inferences in Dynamic Environments with Compositionally Organized Learning To Reason About Novel Experiences (PRIDE with COLTRANE)

Award Information
Agency: Department of Defense
Branch: Defense Advanced Research Projects Agency
Contract: 140D0422C0045
Agency Tracking Number: D2-2711
Amount: $1,654,370.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: ST081-004
Solicitation Number: 08.A
Solicitation Year: 2008
Award Year: 2022
Award Start Date (Proposal Award Date): 2022-08-08
Award End Date (Contract End Date): 2023-08-07
Small Business Information
625 Mount Auburn Street
Cambridge, MA 02138-4555
United States
DUNS: 115243701
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Bryan Loyall
 (617) 491-3474
Business Contact
 Mark Felix
Phone: (617) 491-3474
Research Institution

Current AI systems are brittle to novel changes in the world. This limits their applicability, leads to large engineering efforts to create robustness in spite of the brittleness, and is a cause of unpredictable failures. Both knowledge-based, first-wave AI and data-driven, second-wave AI techniques have been unable to overcome this brittleness. Charles River Analytics and MIT’s Computational Cognitive Science and Probabilistic Computing groups are developing a new, third-wave approach that merges symbolic and sub-symbolic reasoning for effective operation in open worlds. This approach builds on emerging technologies that combine probabilistic programming (PP) and symbolic reasoning to create PRIDE with COLTRANE (Probabilistic and Relational Inferences in Dynamic Environments with Compositionally Organized Learning To Reason About Novel Experiences). In contrast to traditional symbolic reasoning systems, PRIDE with COLTRANE recognizes novelty, synthesizes new representations automatically, and reasons using the new representations to adapt in real-time to novel situations. Unlike traditional learning systems that require large amounts of training data for every situation, PRIDE with COLTRANE uses its knowledge structures to learn about new situations from a very small set of instances and applies the structures again to adapt on the fly.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government