News

 

Home
News
Publications
Members
Projects
Sponsors
Links

GMU
Volgenau School of IT&E
CS Department
AIT Department

2008 | 2007 | 2006 | 2005 | 2004 | 2003 | 2002 | 2001 | 2000 | 1999 | 1998

2008

  • March 2008: NSF has awarded Exprentis Inc. and the Learning Agents Center the Phase II of the project titled "Disciple Technologies for Development, Utilization, and Maintenance of Regulatory Knowledge Bases."
     
  • March 2008: The paper "Teaching Virtual Experts for Multi-Domain Collaborative Planning", by Tecuci G., Boicu M., Marcu D., Barbulescu M., Boicu C., Le V., Hajduk T., was published by the online Journal of Software, Volume 3, Number 3, pp. 38-59.
     
  • February 20, 2008: Vu Le defended his PhD Dissertation in Information technology, titled "Abstraction of Reasoning for Problem Solving and Tutoring Assistants."
     

2007

  • December 2007: The paper "Mixed-Initiative Assumption-Based Reasoning for Complex Decision-Making", Tecuci G., Marcu D., Boicu M., Le V., was published by Studies in Informatics and Control, Volume 16, Number 4, December 2007.
     
  • October 4, 2007: Gheorghe Tecuci participated in the "Sort Thru Hype" panel discussion of the Digital Government Institute's E-Learning Conference, panel summarized in the article entitled "Panelists offer advice on training technology" from the October 9th issue of the Government Executive e-newsletter. The Newsletter’s Quote of the Day also referred to Gheorghe Tecuci.
     
  • August 2007: Mihai Boicu appointed Assistant Professor in the Department of Applied Information Technology of the Volgenau School of IT&E, George Mason University.
     
  • July 2, 2007: Gheorghe Tecuci delivered the keynote address entitled “From Personal Computers to Learning Assistants: Development and Use of Intelligent Agents by Non-Computer Scientists,” at The Third IASTED International Conference on Computational Intelligence, Banff, Canada (see http://www.iasted.org/conferences/keynote-574.html)
     
  • June 22, 2007: Gheorghe Tecuci delivered the talk entitled “Complex Applications of the Disciple Cognitive Assistants” at the Romanian Academy.
     
  • June 5, 2007: Gheorghe Tecuci presented “Intelligent Assistants for Distributed Knowledge Acquisition, Integration, Validation, and Maintenance,” at the Air Force Research Laboratory, Rome, NY.
     
  • June 4, 2007: “Agent Learning for Mixed-Initiative Knowledge Acquisition” by Gheorghe Tecuci and Mihai Boicu, presented at AFOSR PI Meeting, Syracuse, NY.
     
  • Summer 2007: Tecuci G., Boicu M. and Cox M.T. are the guest editors of the AI Magazine Special Issue on Mixed-Initiative Assistants, Volume 28.


  • Spring 2007: Disciple-LTA used in the “Military Applications of Artificial Intelligence: Intelligence Analysis” course at the US Army War College.


  • Spring 2007: Disciple-COG used in the “Case Studies in Center of Gravity Analysis” course at the US Army War College.


  • Spring 2007: Marcel Barbulescu, Cristina Boicu, Mihai Boicu, Dorin Marcu, Vu Le and Gheorghe Tecuci received Certificates of Appreciation from the Air War College.
     
  • Spring 2007: Disciple-COG used in the “Center of Gravity” course at the US Air War College.
     
  • April 5, 2007: “Expert Agent Technology for Knowledge-Intensive Applications,” by Gheorghe Tecuci, Mihai Boicu, Douglas Weidner, Invited Presentation, Track 3 Technology Applications for Successful KM Programs, The 8th Annual Knowledge Management Conference, April 3-5, 2007.


  • February 5, 2007: Marcel Barbulescu presented his PhD Thesis Proposal entitled “Shared Knowledge Repositories for Instructable Agents”.


  • January 5, 2007: “A Tool for Training and Assistance in Emergency Response Planning,” by Tecuci G., Boicu M., Hajduk T., Marcu D., Barbulescu M., Boicu C., Le V., was presented at the Hawaii International Conference on System Sciences, HICSS-40, Hawaii, January 3-6, 2007.


2006

  • December 2006: “Lazy Rule Refinement by Knowledge-Based Agents” Cristina Boicu, Gheorghe Tecuci, Mihai Boicu, was presented at the Fifth International Conference on Machine Learning and Applications (ICMLA'06), Orlando, Florida, USA, 14-16 December 2006.


  • November 2006: Dr. Cristina Boicu was appointed Research Assistant Professor in the Learning Agents Center.


  • November 6, 2006: Cristina Boicu publicly defended her PhD thesis entitled “An Integrated Approach to Rule Refinement for Instructable Knowledge-Based Agents.”


  • September 7, 2006: Dorin Marcu presented his PhD Thesis Proposal entitled “An Approach to the Design and Learning of Interaction Models for Mixed-Initiative Assistants”.


  • August 24, 2006: “Cognitive Assistants for the Analysts” by Gheorghe Tecuci, Mihai Boicu, Cindy Ayers, was presented at the “Analyzing Future National Security Challenges” Proteus Futures Academic Workshop, 22-24 August 2006, Carlisle, Pennsylvania.


  • August 10, 2006: Vu Le presented his PhD Thesis Proposal entitled “Learning and Tutoring Agent Shell: A New Approach to Building Intelligent Tutoring Systems for Expert Problem Solving Knowledge”.


  • July 24, 2006: “Cognitive Assistants for the Analysts: Experiments in the Classroom” by Christopher Fowler, Cindy Ayers, David Cammons, Gheorghe Tecuci, Mihai Boicu, Vu Le, Dorin Marcu, Cristina Boicu, Marcel Barbulescu, was presented by Vu Le at INFORMS Military Applications Society Conference “Homeland Security for the 21st Century” July 24-26, 2006, Mystic Hilton - Mystic, Connecticut.


  • June 15, 2006: Gheorghe Tecuci delivered the talk “Personal Cognitive Assistants for Military Applications,” as part of the BAE SYSTEMS Advanced Information Technologies Distinguished Speakers Series, Arlington, VA


  • Spring 2006: National Science Foundation announced the funding of the STTR Phase I project “Disciple Technologies for Development, Utilization, and Maintenance of Regulatory Knowledge Bases” of Exprentis Inc. and GMU’s Learning Agents Center.


  • Spring 2006: Disciple-LTA used in the “Military Applications of Artificial Intelligence: Intelligence Analysis” course at the US Army War College.


  • Spring 2006: Disciple-COG used in the “Case Studies in Center of Gravity Analysis” course at the US Army War College.


  • May 22, 2006: Gheorghe Tecuci delivered the invited talk “Agent Development by Subject Matter Experts: Case Studies in Psychological Operations and Intelligence Analysis,” as part of the Intelligent Agent Software Development Seminar, MITRE.


  • April 13, 2006: Gheorghe Tecuci delivered the lecture “Intelligent Assistants for Distributed Knowledge Acquisition, Integration, Validation, and Maintenance,” Air Force Research Laboratory, Rome, NY.


  • March 9, 2006: Gheorghe Tecuci delivered the lecture “Development of Personal Cognitive Assistants by Subject Matter Experts, Institute for Cognitive Science and Technology, National Research Council of Italy, Rome.


  • February 9, 2006: Gheorghe Tecuci delivered the lecture “Intelligent Assistants for Center of Gravity Analysis and Other Military Applications of Disciple Agents,” Airpower Research Institute, Montgomery, AL.

2005

  • December 2, 2005: “Learning Agents for Emergency Response Planning: Training and Decision-Making Assistance” by Gheorghe Tecuci, Mihai Boicu, Dorin Marcu, Marcel Barbulescu, Cristina Boicu, Vu Le, Thomas Hajduk, was presented at the Symposium on Information Technology for Emergency Preparedness and Response, organized by the Department of Information and Software Engineering, George Mason University.
     

  • November 2005: Gheorghe Tecuci (cochair) and Mihai Boicu (PC member) co-organized the AAAI 2005 Fall Symposium on Mixed-Initiative Problem-Solving Assistants, Arlington, Virginia, November 4-6, 2005. (See also the AAAI 2005 Fall Symposia website)

  • September 21, 2005: Gheorghe Tecuci delivered the lecture From Personal Computers to Learning Agents as the 2005 IT&E Outstanding Research Faculty Award Recipient (See invitation and picture).

  • July 2005: Mihai Boicu demonstrated Disciple-LTA at AAAI-2005, The Twentieth National Conference on Artificial Intelligence, AAAI-05, Pittsburgh, Pennsylvania, USA, July 9-13 2005.

  • Spring 2005: Gheorghe Tecuci has received the 2005 IT&E Outstanding Research Faculty Award. (picture 1   picture 2)

  • Spring 2005: Cristina Boicu has received the Outstanding Graduate Student Award in Information Technology.

  • Spring 2005: Disciple-LTA used in the Term III “Military Applications of Artificial Intelligence: Intelligence Analysis”

  • Spring 2005: Disciple-COG used in the Term III “Case Studies in Center of Gravity Analysis” course at the US Army War College.

  • March 2, 2005: Gheorghe Tecuci presented “An Approach to Staffbots Development and Maintenance by Subject Matter Experts” at the DARPA Workshop on Virtual Intelligent Agents (Staffbots), Arlington, Virginia.

  • Winter 2005: Disciple-COG used in the Term II “Case Studies in Center of Gravity Analysis” course at the US Army War College.

2004

2003

2002

2001

  •  2001 US Army War College Recognition for LALAB Research
    • Gheorghe Tecuci has been appointed Chair of Artificial Intelligence at the US Army War College for the Academic Year 2001-2002.

    • Mihai Boicu, Dorin Marcu, Bogdan Stanescu, Cristina Cascaval, and Gabriel Catalin Balan (click on a name to veiw the respective certificate) have each received a Certificate of Appreciation from Prof. Douglas Campbell, Director of the Center for Strategic Leadership of the US Army War College. Each certificate states:

          “For exceptional contribution to the United States Army War College during the academic year 2000-2001. Your work on the Disciple-COG research project was instrumental to the development of learning agents for center of gravity determination. Your excellent technical work was a significant contribution to agent development, and your tireless support to the Artificial Intelligence course was key to the smooth integration of that agent technology into the War College curriculum. Your effort and attention to detail are deeply appreciated and reflect great credit upon yourself and George Mason University.

    • Gheorghe Tecuci has received the Coin of the US Army War College Center for Strategic Leadership, in May 2001.

  •  AI Magazine article on Disciple-COA
    The Summer 2001 issue of the AI Magazine contains the LALAB paper "An Innovative Application from the DARPA Knowledge Bases Program: Rapid Development of a Course of Action Critiquer," by Gheorghe Tecuci, Mihai Boicu, Michael Bowman and Dorin Marcu, with a commentary by Murray Burke, the program manager of the DARPA's HPKB and RKF programs.

  •  Successful experiment of developing end-to-end Disciple agents
    We have performed a successful experiment at the US Army War College during which military officers have trained personal Disciple agents to identify center of gravity candidates. At the end of the experiment 7 out of 10 experts agreed, one strongly agreed and two were neutral with respect to the following statement: "I think that a subject matter expert can use Disciple to build an agent, with limited assistance from a knowledge engineer."

  •  The Disciple approach seen as a revolutionary Software Design Methodology
    The special issue on "Software Design Methodologies" of the CrossTalk journal includes an article on the Disciple approach which is introduced by Kevin Richins, the publisher of this issue, as: "This is quite a revolutionary approach that may cause you to rethink traditional defense software development methodologies."

  •  Use of Disciple-CoG/RKF in the "Military Applications of Artificial Intelligence" course at the US Army War College
    Disciple was successfully used in the "Military Applications of Artificial Intelligence" course at the US Army War College during the Spring 2001 session. An improved version will again be used in the Spring 2002 session of this course.

  •  Use of Disciple-CoG/RKF in the "Case Studies in Center of Gravity Analysis" course at the US Army War College
    Disciple was successfully used in the "Case Studies in Center of Gravity Analysis" course at the US Army War College during the Winter 2001 and Spring 2001 sessions. An improved version will again be used in the Winter 2002 session of this course.

  •  SIGNAL Magazine on the LALAB/GMU research
    The February 2001 issue of the Armed Forces Communications-Electronics Association (AFCEA)'s SIGNAL magazine (http://afcea.org/ ) includes the article "Intelligent Agents Get Smarter" by Henry S. Kenyon, that describes the research done in LALAB/GMU.

2000

  •  Collaboration with the Center for Strategic Leadership of the US Army War College on the Center of Gravity Problem
    In the fall of 2000, LALAB has started a collaboration with the Center of Strategic Leadership of the US Army War College to apply the Disciple approach to "Strategic Center of Gravity Determination and Analysis".

  •  Selection for the new DARPA's RKF program.
    Due to the very good results obtained during the HPKB program, the LALAB/GMU has been selected by DARPA to participate in the new Rapid Knowledge Formation program, together with a subset of the teams that have participated in the HPKB program, including research groups from Stanford University, SRI, MIT, and Cycorp. Our project (PI: George Tecuci, Co-PI: Henry Hamburger), called "Collaborative Assistant for Rapid Knowledge Formation and Reasoning", contributes directly to our long term research objective.
    RKF Home Page
    GMU RKF Proposal

1999

  •  Successful experiment in teaching Disciple by normal users.
    One of the most significant research results over the last three years (1997-1999) is the successful knowledge acquisition experiment that took place over one week, in August 1999, at the US Army Battle Command Battle Lab, in Ft. Leavenworth, KS, as part of the DARPA's HPKB program. In this experiment, four military experts with no prior knowledge engineering experience received very limited training in the use of Disciple-COA and then each succeeded in significantly extending the knowledge base of Disciple-COA, receiving only very limited support from a knowledge engineer. To our knowledge, this is the first time that such an experiment has been conducted, and its success demonstrates the feasibility of our long term research objective. At the end of the experiment, the domain experts completed a detailed questionnaire where they gave very high scores to our research. For instance, LTC John N. Duquette, Chief of the Experimentation Division of BCBL stated: "The potential use of this tool by domain experts is only limited by their imagination - not their AI programming skills."
    See some answers to key questions.
    See the evolution of the knowledge base of Disciple-COA during the experiment.
    Browse or download the GMU presentation at the final HPKB meeting in Arlington, October 1999.

  •  Best Results at DARPA's Course of Action Challenge Problem.
    Four research teams participated in the DARPA's HPKB challenge problem called "Course of Action Critiquing": 1) A joint Teknowledge-Cycorp team, 2) The "Expect" research group from the Information Science Institute of the University of Southern California, 3) The "LOOM" research group the Information Science Institute of the University of Southern California, and 4) the "Disciple" research group from LALAB/GMU. Confirming the results obtained during the DARPA's 1998 evaluation, the GMU team distinguished itself by obtaining the best evaluation results among all the participating teams. Moreover, by receiving a score of 114%, it exceeded even the performance of the domain experts that performed the evaluation. This high performance was due to the fact that Disciple-COA was trained by a very competent expert and, as a result, generated many new solutions that were not anticipated by the evaluators. This is very significant because it demonstrates that a very knowledgeable expert can train Disciple to exhibit much of his or her expertise. During the evaluation, we again demonstrated a very high rate of knowledge acquisition, the knowledge base of Disciple increasing by 46% during 8 days (from a size of 6229 simple axioms equivalent to a size of 9092 simple axioms equivalent).
    See the 1999 Course Of Action Challenge Problem Evaluation.
    Browse or download the GMU presentation at the final HPKB meeting in Arlington, October 1999.
    Comparative Results:
    Coverage vs. Recall
    Metric: Recall
    Metric: Precision
    Metric: Overall
    Number of Model Answers Generated
    Number of Test Questions Answered
    Recall by Criteria
    Precision by Criteria
    Additional details on the results are contained in Alphatech's presentation at the final HPKB meeting.

  •  Five papers accepted at AAAI '99 and associated workshops:
    Tecuci G., Boicu M., Wright K., Lee S.W., Marcu D., and Bowman M., "An Integrated Shell and Methodology for Rapid Development of Knowledge-Based Agents", in Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99), July 18-22, Orlando, Florida, AAAI Press, Menlo Park, CA. 1999.

    Boicu M., Wright K., Marcu D., Lee S.W., Bowman M. and Tecuci G., "The Disciple Integrated Shell and Methodology for Rapid Development of Knowledge-Based Agents", in Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99), Intelligent Systems Demonstrations, July 18-22, Orlando, Florida, AAAI Press, Menlo Park, CA. 1999.

    Lee S.W. and Tecuci G., "Knowledge Base Revision through Exception-driven Discovery and Learning", in the Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99), Student Abstract Program, July 18-22, Orlando, Florida, AAAI Press, Menlo Park, CA. 1999.

    Tecuci G., Boicu M., Wright K. and Lee S.W., "Mixed-Initiative Development of Knowledge Bases", in Proceedings of the Sixteenth National Conference on Artificial Intelligence Workshop on Mixed-Initiative Intelligence, July 18-19, Orlando, Florida, AAAI Press, Menlo Park, CA. 1999.

    Boicu M., Tecuci G., Bowman M., Marcu D., Lee S.W. and Wright K., "A Problem-Oriented Approach to Ontology Development", in Proceedings of the Sixteenth National Conference on Artificial Intelligence Workshop on Ontology Management, July 18-19, Orlando, Florida, AAAI Press, Menlo Park, CA. 1999.

  •  Top team of the 1999 ACM Contest joins LALAB.
    Bogdan Stanescu and Liviu Panait have joined LALAB in August 1999. They are members of the Bucharest University team that has won the 4th place at the 1999 ACM International Collegiate Programming Contest World Finals, Eindhoven, The Netherlands. Previously they had won the 1st place at the 1998 ACM South-Eastern European Regional Contest. A total of 1,457 teams all over the world participated in the contest. The final standings are available on the ACM site.

  •  Successful ontology reuse with Disciple.
    With the development of Disciple-COA, in the second part of the DAPRA's HPKB program (98-99), we have built, for the first time, the knowledge base of a Disciple agent around an ontology created by another group (Teknowledge and Cycorp), demonstrating both the feasibility of knowledge reuse with the Disciple approach, and the generality of the Disciple rule learning and refinement methods. Moreover, the Disciple-COA agent was taught even more rapidly than the Disciple-workaround agent, and has again demonstrated a significantly higher performance than the other developed systems.

1998

  •  Selection for EFX'98.
    Based on the evaluation results in the HPKB program, the Disciple-workaround system was selected by DARPA and Alphatech to be further extended and was integrated by Alphatech into a larger system that supports air campaign planning by the JFACC and his/her staff. The integrated system was one of the 17 systems selected from 84 systems to be demonstrated at EFX'98, the Air Force's annual show case of the promising new technologies.

  •  Best results at DARPA's Workaround challenge problem.
    During the first part of the HPKB program we developed the Disciple-Workaround integrated system that demonstrated a capability by which a knowledge engineer can rapidly build a knowledge base capturing knowledge from Military Engineering manuals. During the 17 days of DARPA's 1998 evaluation, the knowledge base of Disciple was increased by 72% with almost no decrease in performance (Cohen et al., 1998: The DARPA High-Performance Knowledge Bases Project, AI Magazine, 19(4), 25-49). The resulting workaround reasoner also achieved the best scores among all the teams that participated in the workaround challenge problem (see the 1998 Workaround Challenge Problem Evaluation).
    It is relevant to mention that these results were obtained by a GMU team that started as an "innovative technology component" team and ended-up building an integrated system by itself. For comparison, the other two teams that developed integrated systems for the Workaround Challenge Problem were the following: 1) ISI-SAIC (consisting of two research groups from the Information Science Institute of the University of Southern California and one research group from SAIC) and 2) TFS (consisting of a research group from Teknowledge and one from Cycorp).
    In a journal paper describing the various approaches to the workaround challenge problem, John Kingston of Edinburgh University states: "The rapid development of GMU's system highlighted its integrated knowledge acquisition tool as being its greatest strength. Over the fortnight of testing, GMU added 150 concepts, 100 tasks and 100 problem-solving rules to their knowledge base, representing a 20% increase in concepts, a 100% increase in tasks and a 100% increase in rules. This rate of knowledge acquisition suggests that GMU's system may indeed be able to achieve one of the Holy Grails of knowledge acquisition: rapid, accurate and direct knowledge entry by an expert without intervention from a knowledge engineer. GMU's system was also capable of reasoning about most aspects of the workarounds problem - indeed, it generated a few (correct) solutions that had not been considered by the expert."
    See the HPKB Challenge Problem - Individual Results (Y1).

  •  LALAB selected for DARPA's HPKB program.
    A very significant development and scaling up of the Disciple approach was done as part of DARPA's High Performance Knowledge Bases (HPKB) program (1997-1999) that supported Artificial Intelligence research groups from some of the top universities, research institutes and companies in the country (including Stanford, MIT, Carnegie Mellon Univ., Northwestern Univ., U.Mass, SRI, USC/ISI, CyCorp and Teknowledge). GMU was supported by the AFOSR grant F49620-97-1-0188. In the HPKB program, each research group had to develop intelligent knowledge-based agents for solving specially designed challenge problems, and has been evaluated on how well it has solved these problems. The GMU team has obtained the best scores among all the participating teams for both challenge problems that it has addressed, and has done this while very rapidly developing the knowledge bases of the agents, as described above.

  •  Book on the Disciple approach.
    Tecuci G. (with contributions from the LALAB members Dybala T., Hieb M., Keeling H., Wright K., Loustaunau P., Hille D., Lee S.W.), BUILDING INTELLIGENT AGENTS: An Apprenticeship Multistrategy Learning Theory, Methodology, Tool and Case Studies, Academic Press, 1998, ISBN:0126851255.

  •  LALAB wins Best Paper Award at ITS'98.
    As part of DARPA's Computer-Aided Education and Training Initiative program (1995-1997) and NSF's Collaborative Research on Learning Technologies program (1996-1998), LALAB developed the Disciple Toolkit and used it to build and train an Assessment Agent for the higher order thinking skills of middle school History students. The paper "Tecuci G. and Keeling H., Developing Intelligent Educational Agents with the Disciple Learning Agent Shell", describing how the Assessment Agent was taught to generate test questions for students, received the Best Paper Award at the 4th International Conference on Intelligent Tutoring Systems, San Antonio, Texas, August 1998.

Last updated on 04/18/08