WASHINGTON – New trusted-computing software developed by BAE Systems could help the U.S. Department of Defense (DOD) build confidence in decisions and intelligence produced by machine learning algorithms, company officials say. C4ISRnet reports. Continue reading original article
The Military & Aerospace Electronics take:
10 Aug. 2020 -- BAE Systems has delivered the MindfuL software program to the U.S. Defense Advanced Research Projects Agency (DARPA) is designed to increase transparency in machine learning and artificial intelligence (AI) systems by auditing them to provide insights about how these systems reached their decisions.
BAE Systems developed the MindfuL software for the DARPA Competency-Aware Machine Learning (CAML) project, which focuses on competency-awareness machine learning, in which an autonomous system can self-assess its task competency and strategy, and express both in a human-understandable form.
This competency-awareness capability contributes to the goal of transforming autonomous systems from tools into trusted, collaborative partners, DARPA officials say. Competency-aware machine learning software will enable machines to control their behaviors to match user expectations and enable human operators quickly and accurately to gain insight into a system’s competence in complex, time-critical, dynamic environments. CAML, in short, seeks to improve human-machine teaming.
John Keller, chief editor
Military & Aerospace Electronics