You are here

Open Call for Science and Technology Created by Early-Stage (e.g. University) Teams

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: FA8649-19-P-A046
Agency Tracking Number: F19B-001-0176
Amount: $24,906.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: AF19B-T001
Solicitation Number: 2019.2
Timeline
Solicitation Year: 2019
Award Year: 2019
Award Start Date (Proposal Award Date): 2019-08-02
Award End Date (Contract End Date): 2020-08-02
Small Business Information
611 W. Yellow Springs Fairfield Rd, FAIRBORN, OH, 45324
DUNS: 081333321
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: N
Principal Investigator
 Brandon Minnery
 (301) 875-6855
 brad@kairos-research.com
Business Contact
 Ebi Maki
Phone: (937) 823-9516
Email: ebi@kairos-research.com
Research Institution
 Kansas State University
 Pascal Hitzler
 2 Fairchild Hall, 1601 Vattier Street
Manhattan, KS, 66506
 (785) 532-6350
 Nonprofit college or university
Abstract
Assess the feasibility of a novel technology which automatically generates human-understandable explanations of an artificial intelligence (AI) algorithms decisionsfor example, a deep neural networks (DNNs) classification decisions. Our technology, called EMERALD (Explainable Machine Reasoning through the Application of Linked Data), is designed to improve trust and transparency within human-in-the-loop AI systems by providing the human operator with an informed basis for accepting/rejecting/modifying the decisions of the AI. EMERALD works by leveraging background information contained within knowledge graphs to infer an AIs internal model of the world based on its external behaviors. EMERALD is designed to take advantage of ever-increasing volumes of structured semantic information (linked data) available on the Web. The recent proliferation of explicitly structured Semantic Web data (two prominent examples being Wikidata and the Google Knowledge Graph) has occurred at the same time as powerful black box machine learning algorithms such as DNNs have become ubiquitous. Because these algorithms often encode information implicitly, their thought processes defy easy interpretation. With EMERALD, we will capitalize on one AI trend (knowledge graphs) to improve the transparency and trustworthiness of another (machine learning). As such, our approach resides at the vanguard of so-called third-wave contextual AI Research.

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

US Flag An Official Website of the United States Government