Summary of: “Establishing Trust between two Machines" held on Friday, April 21, 2017 from 8:00-10:00 AM.
Establishing trust and trustworthiness among two or more computing entities has always been a challenge, but a necessary step prior to secure interaction. This challenge is further complicated in human-machine learning applications where parties to an interaction can dynamically learn and alter their behaviors. Dr. Levitt has developed techniques to establish trust in a machine learning setting. His techniques draw from methods that people use to establish trust and formalize these methods with probabilistic modeling. The resultant techniques can be used in a variety of commercial applications in autonomy such as driverless cars.
This discussion focused on trust and trustworthiness in machine learning applications, led by Dr. Tod Levitt, Research Professor at George Mason University. Here is a link to his CV.
Dr. Levitt is an acknowledged leader in development of advanced capabilities for evidential reasoning in large-scale, high dimensional model analysis including operations applications in multi-sensor fusion, SAR, IR, and EO image understanding, ground robot vision, air to ground surveillance systems and C4ISR systems supporting multiple military intelligence, planning and command and control applications.
He has led the development of a diverse family of advanced information software systems built to handle real world data under complex operating conditions. These systems include a fully automated middle-Eastern armor unit detector for the U.S. Army that was evaluated to perform at expert imagery analyst levels on wide-area, low resolution Desert Storm SAR, and a system for automated diagnostic measurement from digital x-rays of the hand that was employed in clinical care at the San Francisco Veterans Administration Medical Center.