the Computer Science Department

CMU CS Machine Learning Group

The Machine Learning Group is part of the Center for Automated Learning and Discovery (CALD), an interdisciplinary center that pursues research on learning, data analysis and discovery.

Machine learning is concerned with design and the analysis of computer programs that improve with experience.

``Ever since computers were invented, it has been natural to wonder whether they might be made to learn. If we could understand how to program them to learn the impact would be dramatic. The practice of computer programming would be revolutionized as many tedious hand-coding tasks would be replaced by automatic learning methods. And a successful understanding of how to make computers learn would most likely yield a better understanding of human learning abilities and disabilities as well.'' (from Tom Mitchell's new book ``Machine Learning'')

group picture
Avrim Blum Interested in machine learning theory, algorithm design and analysis. See his papers.
Jaime Carbonell Interested in integrated intelligent systems (seamless integration of machine learning, planning, problem-solving, execution monitoring and communication), and in multi-lingual natural language processing.
Scott Fahlman Interested in artificial neural networks, software development environments (Gwydion/Dylan), and high-performance processing of biomedical images.
Tom Mitchell Interested in machine learning, with applications to robotics, information retrieval and database mining.
John Lafferty Interested in speech and natural language processing, statistical learning algorithms, probability and information theory.
Andrew W. Moore Interested in machine learning applications to robots, factories and other complex control systems.
Reid Simmons Interested in mobile robot planning and task-level control, probabilistic planning and reasoning intelligent agents.
Katia Sycara Interested in distributed coordination of intelligent software agents, case-based reasoning and learning, and constraint-directed reasoning.
Sebastian Thrun Interested in machine learning applications to robotics, learning architectures, reinforcement learning, and the integration of symbolic and neural computation. See his papers.
Dave Touretzky Interested in representation and processing of information in the brain.
Raul Valdes-Perez Scientific discovery and computers, e.g., interactive programs to carry out scientific reasoning at its highest levels. Practical deployment of tools as scientist's assistants. Implications for future organization of science.
Manuela Veloso Interested in planning and learning, machine learning applied to signal understanding, experience-based autonomous agents with high-level and low-level task reasoning, collaborative and adversarial planning and learning in dynamic domains.
Alex Waibel Interested in speech, language, speech translation, multimodal interfaces, neural nets and machine learning.
Michael Witbrock
Michael Cox Interested in case-based learning, derivational analogy, multistrategy learning, rationale capture and replay in planning, memory (especially forgetting), introspection.
Jeff Schneider
Graduate Students
Deb Baker Douglas Beeferman
Jim Blythe
Justin Boyan
Aaron Courvile Scott Davies
Nathaniel Daw Frank Dellaert
Kan Deng
Rujith DeSilva
Robert Driskill
Eugene Fink
Dayne Freitag
Mark Fuhs
Matthew Glickman Rich Goodwin
Geoffrey Gordon Karen Haigh
Angela Kennedy Sven Koenig
Ken Lang Shyjan Mahamud
Daniel Nikovski Scott Reilly
Henry Rowley
Sean Slattery
Yury Smirnov Peter Stone
Joseph O'Sullivan
Eric "Astro" Teller
Belinda Thom
James Thomas
William Uther
Santosh Vempala
Thorsten Joachims Stefan Waldherr
Other visitors: please send me mail
Learning from Text and the Web See Text Learning Lab Homepage
Learning noisy linear separators Contact Avrim Blum
Algorithms for focusing on relevant features Contact Avrim Blum
CRAWL A computational theory of rodent navigation, including neural representations of spatial information and the learning of new environments by exploration. Contact Dave Touretzky or Mark Fuhs
XAVIER and AMELIA Autonomous mobile robots that learn
The Skinnerbots project A theory of operant conditioning with application to trainable robots. Contact Dave Touretzky, Aaron Courvile, or Nathaniel Daw
WebWatcher A tour guide for the World Wide Web
PRODIGY A high-speed planning and learning architecture
Detection of faces and other objects in images, using neural network-based techniques See the on-line demo
Various projects related to speech, language, speech translation, and multimodal interfaces
Planning and Learning by Analogical/Case-Based Reasoning
Planning and Search Algorithms
Minds for Robots: Agents that Plan, Execute, and Learn
Collaborative and Adversarial Planning and Learning: RoboSoccer and Bolo
Machine Learning for Signal Understanding
Rationale Capture and Reuse in Mixed-Initiative Planning
Machine Learning
Machine Learning Theory
Introduction to Artificial Neural Networks
Computational Models of Neural Systems.
Introduction to Artificial Intelligence
Information Theory
Other Resources
Center for the Neural Basis of Cognition (a joint center with the University of Pittsburgh)
The Reinforcement Learning Homepage
The Learning Lab Homepage
list of conferences related to machine learning
The Neural Information Processing Systems (NIPS) Conference
David Aha's list of machine learning researchers and resources
comment comment maintained by