1. Kansas State University
  2. »Division of Communications and Marketing
  3. »K-State Today
  4. »Computer science center to collaborate on Phase 2 US Air Force contract to develop...

K-State Today

September 24, 2020

Computer science center to collaborate on Phase 2 US Air Force contract to develop explainable artificial intelligence

Submitted by Mary Rankin

Pascal Hitzler

A collaboration of Kairos Research, Dayton, Ohio, with the Kansas State University Center for Artificial Intelligence and Data Science in the Carl R. Ice College of Engineering has been awarded a Phase 2 contract by the U.S. Air Force to develop novel methods for increasing the explainability of state-of-the-art machine-learning algorithms.

The Kairos-led team will test a new approach for rendering the decision outputs of deep learning systems more understandable to human users. Specifically, it will investigate whether background information contained in external knowledge graphs can be used to automatically explain the reasoning process of deep neural networks performing image classification.

Lead on the project is Brad Minnery, CEO of Kairos Research, and heading the K-State team is Pascal Hitzler, professor and Lloyd T. Smith Creativity in Engineering chair in computer science department and director of the Center for Artificial Intelligence and Data Science.

The Kairos and K-State team's cutting-edge research is funded by the Department of Defense Small Business Technology Transfer, or STTR, program, and is managed through the Air Force's innovative AFWERX unit. The goal of the STTR program is to encourage joint ventures between small businesses and nonprofit research institutions, including universities.

"Modern AI systems have achieved impressive performance in many domains, but their inner workings are something of a black box," Hitzler said. "By making AI more transparent, we can potentially do a better job at predicting the conditions under which an AI system is likely to fail. This in turn could allow us to develop more robust AI algorithms from the start."