RI | People | David Cohn

Text only version of this site

David Cohn
Research Scientist (Adjunct)

No longer a member of RI.

For more information, see my personal homepage.

Jump to: Research interests | Keywords | Labs & Groups | Projects | Publications

Research interests

• 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?

• 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?

Research interest keywords

artificial intelligence, machine learning, and mobile robots

Past Labs & Groups

Auton Lab - We build practical large-scale deployments of very highly autonomous self-improving systems.

Robot Learning Lab - Pursuing research on robot learning, mobile robotics, multi-robotics, human robot interaction, and basic machine learning.

Past Projects

Auton Project - Research into Autonomous Learning Software Systems

Personal Robotic Assistants For The Elderly - Pearl will help researchers explore the ways autonomous mobile robots can help the elderly live independently in their own homes.

Publications

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• cGraph: A Fast Graph-Based Method for Link Analysis and Queries
  J.M. Kubica, A. Moore, D. Cohn, and J. Schneider
  Proceedings of the 2003 IJCAI Text-Mining & Link-Analysis Workshop, August, 2003, pp. 22-31. [Abstract]
  Download: pdf [121 KB], ps.gz [97 KB] copyrighted

• Finding Underlying Connections: A Fast Graph-Based Method for Link Analysis and Collaboration Queries
  J.M. Kubica, A. Moore, D. Cohn, and J. Schneider
  Proceedings of the 2003 International Conference on Machine Learning, AAAI Press, August, 2003, pp. 392-399. [Abstract]
  Download: pdf [88 KB] copyrighted