Christopher Brown, Ph.D.

Discipline: Computer Science
Focus: Artifical Intelligence
Email:
CV: Full CV for Christopher Brown

Intelligent agents can be investigated reductionistically, holistically, in simulation or in the real world. Methodologically, there are decisions to be made along the spectrum (or within the
multi-dimensional space) with axes something like ``innate'',`learned'', ``developed''. It seems we understand how to program capabilities explicitly, and we have some models of certain forms of adult
learning, but that other forms (one-time learning, say) and all of development are still quite mysterious. Human symbolic reasoning is quite recent evolutionarily, and language even more so. Certainly there have been more convincing successes in symbolic AI than there have been in automating the primal infrastructure capabilities of
vision and motor control, but one wonders if this sensorimotor infrastructure will ultimately prove necessary for advanced artificial intelligence.

Biography

Chris Brown (BA Oberlin 1967, PhD U. Chicago 1972) is Professor of
Computer Science at the University of Rochester. He has been at Rochester
since finishing a postdoctoral fellowship at the School of Artificial
Intelligence at the University of Edinburgh in 1974 (the leading
European research center of that time).
He spent two years heading the software development of the PADL-2
solid modeling package from the Production Automation Project at
Rochester. He was chairman of his department from 1981-1984. His
current research interests are computer vision and robotics,
especially integrated parallel systems performing animate vision (the
interaction of visual capabilities and motor behavior).

He is widely published in many areas of computer vision, artificial
intelligence, and robotics.
With his Rochester colleague Dana Ballard, he is
coauthor of what was the leading textbook in the field for many years,
COMPUTER VISION (1982).
Rochester's vision research was reported in two (1993
and 1994) special issues of the International Journal of Computer
Vision, devoted to high- and low-level active vision. He edited the
first two volumes of ADVANCES IN COMPUTER VISION for Erlbaum and (with
D. Terzopoulos) REAL-TIME COMPUTER VISION (1994), from Cambridge
U. Press. He is the co-editor of VIDERE, the first entirely on-line
refereed computer vision journal (MIT Press). In 1995 and 1996 he was
an invited speaker at the Australian computer vision conference and
the International Conference on Pattern Recognition in Vienna.

His three most recent PhD students (2002 -- 2005)
did research in infrared tracking and
face recognition, in features and strategies for scene classification,
and in reconstructing 3-D shape and lighting information for use in
augmented reality. He supervised the undergraduate team that
twice won the AAAI Host Robot competition (and came third in the Robot
Rescue competition in 2003)