[]
The ultimate goal of AI research is to provide the tools, techniques, and methods for building usable systems that make decisions or assist in making decisions that model and "understand" the world, gather relevant knowledge, and act responsibly. In many cases, the decisions and actions are associated with high risks, and certain assurance or robustness is required from the system that uses AI components. What are the ultimate questions that we need to answer in order to build the required runtime robustness for our systems?
We'll explore the central role that three types of unknowns play in our quest for robustness. These are the unobserved entities that need our research attention to make any assurance guarantees. First, we'll analyze the unknown observations that we need to deal with at runtime. Next, we'll explore the unknown features – the additional dimensions along which we need to reason and that are needed to rely upon at decision time. Finally, we'll discuss the unknown constraints – the unknown functions that we need to optimize against.
Co-sponsored by: Seattle University Student Chapter
Speaker(s): Dragos Margineantu, PhD
Agenda:
5.30 PM to 6.00 PM Networking and Light Dinner "Pie Day Specials"
6.00 PM to 6.05 Welcome by Seattle Section Chair
6.05 PM to 6.50 PM Techtalk
Room: Room #: Sinegal 100, Bldg: Jim and Janet Sinegal Center for Science and Innovation, Seattle University, 901 12th Ave, Seattle, WA 98122, Seattle, Washington, United States, 98122, Virtual: https://events.vtools.ieee.org/m/410555
This event has passed.
