Professor Paul Compton

Paul_Compton

Research Expertise

Professor Compton was involved in early expert system development. To overcome the problems with these systems he pioneered incremental knowledge acquisition techniques allowing complex knowledge-based systems to be built and modified whilst in use. His experimental research to date, focuses on the demonstration of participant’s ability to add preferences as a way of changing the behaviour of digital agents in an interactive environment. This research is closely related to machine learning, the key difference being that agent learning is carried out automatically if sufficient data is available, where in the RDR approach the agent can be taught based on a single instance. Some of these techniques have been commercialised in Australia and Korea; in Australia about 20,000 patient reports per day are interpreted and highly patient-specific reports issued, using knowledge-based systems developed by pathologists as part of their standard daily duties. Since 1995 Compton has been Head of School, Associate Dean and once again Head of School of the largest School at UNSW.

Qualifications

  • Master of Science (Biophysics) The University of New South Wales, 1975
  • Bachelor of Science (Physics) The University of New South Wales, 1969

Current Appointment

  • Professor, The University of New South Wales.

Career-best Publications (in the area of knowledge acquisition)

  • Cao, T., Martin E., and Compton, P. “Evolutionary Document Management and Retrieval for Specialised Domains on the Web.” International Journal of Human-Computer Studies, 60.2. 2004: 201-241.
  • Kim, M., and Compton, P. “Evolutionary Document Management and Retrieval for Specialised Domains on the Web.” International Journal of Human-Computer Studies 60 (2) 2004: 201-241.
  • Suryanto, H. and Compton, P. “Invented Predicates to Reduce Knowledge Acquisition.” Proceedings of the IJCAI-2003 Workshop on Mixed-Initiative Intelligent Systems. Acapulco Mexico, 9-15 Aug. 2003. Tecuci, G., Aha, D., Boicu, M., Cox, M., Ferguson, G. and Tate, A. (eds) Mexico: IJAC, 2003: 107-114.
  • Mahidadia, A. and Compton, P. “Assisting Model-Discovery in Neuroendocrinology.” Discovery Science: 4th International Conference, DS2001. Jantke, K. P. and Shinohara, A. (eds) Washington: Springer, 2001: 214-227.
  • Compton, P. and Richards, D. “Generalising Ripple-Down Rules.” Knowledge Engineering and Knowledge Management (12th International Conference, EKAW 2000). Dieng, R. R. and Corby, O. (eds) Berlin: Springer, 2000: 380-386.
  • Compton, P. “Simulating Expertise.” Proceedings of the 6th Pacific International Knowledge Acquisition Workshop, Compton, P., Hoffmann, A., Motoda, H. and Yamaguchi, T. (eds) Sydney: The University of New South Wales, 2000: 51-70.
  • Compton, P., Preston P., Kang B. and Yip, T. “Local Patching Produces Compact Knowledge Bases.” A Future for Knowledge Acqusition: Proceedings of EKAW ’94. Steels, L., Schreiber, G. and Van de Velde, W. (eds) Berlin: Springer Verlag, 1994: 104-117.
  • Compton, P., Edwards G., Srinivasan A., Malor R., Preston P., Kang, B. and Lazarus, L. "Ripple Down Rules: Turning Knowledge Acquisition Into Knowledge Maintenance.” Artificial Intelligence in Medicine 4. 1992: 47-59.
  • Compton, P. J. and Jansen R. “A Philosophical Basis for Knowledge Acquisition.” Knowledge Acquisition 2. 1990: 241-257.
  • Horn, K., Compton, P.J., Lazarus, L. and Quinlan, J.R. “An Expert System for the Interpretation of Thyroid Assays in a Clinical Laboratory.” Aust Comput J 17.1. 1985: 7-11.

Further details: www.cse.unsw.edu.au/~compton/