ABSTRACT

In recent times, we often hear a call for the governance of AI systems, but what does that really mean? In this talk, I will first adopt a control theory perspective to explain governance that determines the reference input via value alignment, data scientists acting as the controller to meet the values in a machine learning system, and facts captured in transparent documentation as the feedback signal. I will then adopt a nursing theory perspective to explain how the control theory perspective lacks caring and the need for a carative approach that starts with the real-world problem as experienced by the most vulnerable people. I will conclude with an example of a project on using machine learning to evaluate applicants for home solar panel systems in rural India.

BIO

Kush R. Varshney is a distinguished research scientist and senior manager at IBM Research – T. J. Watson Research Center where he leads the Trustworthy Machine Intelligence department and the IBM Science for Social Good initiative.