David A. Cohn
(without winter plumage)
Adjunct Research Scientist with the
of Carnegie Mellon University
Chief Technology Officer for DigitalMC
Managing Editor for the Journal of Machine Learning Research
Nefarious past lives: Principal Scientist for Burning Glass Technologies, Research Scientist at Just
Research (a.k.a. JustSystem Pittsburgh Research Center).
Survivor of the Adaptive Systems Group at Harlequin,
Inc. and erstwhile Postdoctoral Associate with the MIT Department
of Brain and Cognitive Sciences and the Center
for Biological and Computational Learning.
Learning structure from document bases – the vast majority
of available electronic documents reside in unstructured document bases. Hypertext remains woefully inadequate:
it is labor-intensive, static, one-directional, and limited to the perspective of the hypertext
author. And when we move beyond the traditional text document to audio, video, and other forms of recorded information, even the rudimentary benefits of hypertext are missing.
Can we automate the extraction of relationships between documents
to generate a dynamic structure that lets users navigate and manipulate unstructured document bases at the conceptual level?
Alternative models of robotics (a.k.a "moving bits, not bolts") –
traditional robots require the ability to sense, compute, act on the world
and, optionally, communicate. By letting communication substitute for some
of these other abilities, can we build smaller, simpler, and yet more powerful
robotic agents? What uses might we have for a "symbot" whose only ability
to act is by communicating with its environment? What about a thin-client
robot ("thin-bot"), which does no computation of its own, but acts as the
eyes and hands of one or more remote computer?
Also dabbling in: stochastic scheduling, decision support, optimization
and statistical pattern recognition.
Active learning - many learning problems in robotics, pattern recognition,
and information retrieval afford chances for the learner to select or influence
the training data it receives. How should it select training data to learn
most quickly, for the least cost?
David A. Cohn (David.Cohn@acm.org)