Douglas Pearson (Douglas John Pearson)

Contact Information

Phone: (206) 675-1518
E-mail:  

On-line Publications

My Thesis

Other Papers

• Correcting Imperfect Domain Theories: A Knowledge-Level Analysis.

in Machine Learning: Induction, Analogy and Discovery, edited by Susan Chipman and Alan Meyrowitz, Kluwer Academic Press, 1992.
This is about the types of errors you can have in an agent's knowledge of the world.
 
• A symbolic solution to intelligent real-time control.

in Robotics and Autonomous Systems 11 (1993) (or try Elsevier Publishers).
This is about designing a rule-based system to fly a simulated plane in real-time.
 
• Combining learning from instruction with recovery from incorrect knowledge.

in Machine Learning 95 Workshop on "Agents that learn from other agents" (1995)
This is about joining together two learning systems, one that corrects mistakes during problem solving and the other that learns from English instructions.
 
• Active Learning in Correcting Domain Theories: Help or Hindrance?

in AAAI Symposium on Active Learning (1995)
This is about the relative merits of learning by doing, rather than learning by being given carefully chosen sample problems.
 
• Toward Incremental Knowledge Correction for Agents in Complex Environments.

to appear in Machine Intelligence 15 (1999)
This is a general overview of my system that learns to correct mistakes as it solves problems. The system is called IMPROV.
 
• Learning Procedural Planning Knowledge in Complex Environments

to appear in AAAI-96 Student Abstract Program (1996).
This is a one page summary of my thesis work.
 
• Knowledge-directed Adaptation in Multi-Level Agents.

in AAAI-96 Workshop on Intelligent Adaptive Agents (1996).
This is about learning at different time-scales within a single system.
 
• Dynamic Knowledge Integration during Plan Execution.

in AAAI-96 Fall Symposium on Plan Execution: Problems and Issues (1996).
This is about how tasks and environments contrain the way plans can be built and used.

Keywords: Machine Learning, Intelligent Agents, Error Recovery, Theory Revision, Instruction, Induction, IMPROV, Soar, Production Rule Systems, Procedural Knowledge

• Example-driven Diagrammatic Tools For Rapid Knowledge Acquisition.

in Visualizing Information in Knowledge Engineering (2003)
This is about a tool we're building that lets users construct intelligent systems through building a series of diagrams


Keywords: Knowledge acqusition, behavior acquisition, diagrams, visualization, example-driven, human behavior models, rule based.

• Redux: Example-Driven Diagrammatic Tools for Rapid Knowledge Acquisition.

in Behavior Representation in Modeling and Simulation (2004)
This is more about our tool, Redux, that lets users construct intelligent systems through building a series of diagrams


Keywords: Knowledge acqusition, behavior acquisition, diagrams, visualization, example-driven, human behavior models, rule based.

• Learning through Interactive Behavior Specifications

in AAAI Symposium on Mixed-Initiative Problem Solving (2005)
This is about combining Redux (our rapid graphical knowledge acquisition tool) with a learning-by-observation machine learning tool.


Keywords: Knowledge acqusition, behavior acquisition, diagrams, visualization, example-driven, human behavior models, learning by observation, machine learning, rule based.

• Incremental Learning of Procedural Planning Knowledge in Challenging Environments

In Computational Intelligence on "Learning to Improve Reasoning" (November 2005)
• Storm: A Framework for Biologically-Inspired Cognitive Architecture Research

In 8th International Conference on Cognitive Modeling, July 2007, Ann Arbor, Michigan

Soar Research Information

To see an example of data-chunking using a method proposed by Rick Lewis a few workshops back, click here for a tar file. Read the READ.ME file for more information.
 

Tag-o-Rama

Home Information

Phone: (206) 675-1518

After hours, I enjoy a wide range of sports, especially badminton which isn't too popular here in the U.S.

Born and bred in Oxford, England...

Did my Bachelor's degree at the University of St. Andrews in Scotland. That's the (little) second inlet on the right going up the east coast (the first, big one's the Firth of Forth--that's where Edinburgh is).

Try out a Java Script to compute today's date and time. Or try out a CGI script to read a form. Or another to get your environment variables. Or some straight Java.
 

Check on usage counters.
 

Douglas Pearson ) [2007]