Human-Agent Teamwork for Information Discovery and Reporting

Speaker
Danko Nebesh
Senior Computer Scientist, Computer and Information Sciences Research Group, National Security Agency

When
-

Where
Newell-Simon Hall 1305 (Michael Mauldin Auditorium)

Description

The relationship between people and computation is currently that of an artisan to a tool. This is certainly true in the area of knowledge discovery and development. We make queries and get results. We run algorithms and get ordered and clustered results. We specify rules and get behavior. We’re on the verge of being able to ask questions and get answers. We are not able to simply say why we need information and get what we need in response. Our objective is to shift from using computation as a tool for gathering information to a tool for building knowledge in a collaborative environment. We believe this end-state will be a mixed-initiative environment in which teams of analysts and autonomous agents work together to achieve common knowledge development goals. This talk will focus on how we are addressing the interaction between analysts and their artificial research assistants.

Speaker's Bio

Danko Nebesh is a senior computer scientist at the Department of Defense where he has worked since 1986. In 1997 he received his PhD in Computer Science at The George Washington University. He received his MS in Computer Science from The Johns Hopkins University and his BS in Computer Engineering from Case Western Reserve University. His research interests include: visualization, HCI, programming languages, and software agents. Currently Nebesh serves as the program manager for the Knowledge Computing program. His work includes partnering with universities, industry research offices, and the Department of Energy national laboratories.