Abstract
There is no doubt that the most fundamental method of knowledge acquisition is discovery, but the AI subfield of Knowledge Acquisition neither studies nor uses discovery methods. We argue that machine discovery is approaching the stage at which it can be useful to knowledge acquisition in two ways: as a source of useful techniques, and as a model of unified knowledge representation and application. We present the discovery system FAHRENHEIT and we discuss its various real-world applications: automated experimentation and discovery in a chemistry laboratory, mining databases for useful knowledge, and others, demonstrating FAHRENHEIT's potential as a knowledge acquisition aid. Finally, we discuss the new developments in the area of discovering basic laws and hidden structure, and we note that automation of modeling would close the cycle of automated knowledge acquisition and application.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Boose, J.H., & Gaines, B.R. (1989) Knowledge Acquisition for Knowledge-Based Systems: Notes on the State-of-the-Art. Machine Learning, 4, 377–394.
Falkenhainer, B.C. (1987) Scientific Theory Formation Through Analogical Inference, Proceedings of Fourth International Workshop on Machine Learning, Los Altos, CA: Morgan Kaufmann Publ., 218–229.
Falkenhainer, B.C., & Michalski, R.S. (1986) Integrating Quantitative and Qualitative Discovery: The ABACUS System, Machine Learning, 1, 367–401.
Falkenhainer, B.C., & Rajamoney, S. (1988) The Interdependencies of Theory Formation, Revision, and Experimentation, Proceedings of the Fifth International Conference on Machine Learning. Morgan Kaufmann Publ.: Los Altos, CA, 353–366.
Fischer, P., & Żytkow, J. (1990) Discovering Quarks and Hidden Structure, in: Ras Z. ed. Methodologies for Intelligent Systems 5, Elsevier, New York, NY, 362–370.
Kocabas, S. (1991) Conflict Resolution as Discovery in Particle Physics. To be published in Machine Learning, 6.
Kodratoff, Y. & Tecuci, G. (1989) The Central Role of Explanations in DISCIPLE, in Morik K. ed. Knowledge Representation and Organization in Machine Learning, Springer-Verlag, Berlin, 135–147.
Kulkarni, D., & Simon, H.A. (1987) The Processes of Scientific Discovery: The Strategy of Experimentation, Cognitive Science, 12, 139–175.
Langley, P.W., Simon, H.A., Bradshaw, G., & Żytkow J.M. (1987) Scientific Discovery; An Account of the Creative Processes. Boston, MA: MIT Press.
Langley, P.W., & Żytkow, J.M. (1989) Data-Driven Approaches to Empirical Discovery. Artificial Intelligence, 40, 283–312.
Morik, K. (1989) Sloppy Modelling, In Morik K. ed. Knowledge Representation and Organization in Machine Learning, Springer-Verlag, Berlin, 107–134.
Mozetic, I. (1987) The role of abstraction in learning qualitative models. Proc. Fourth Int. Workshop on Machine Learning. Morgan Kaufmann, 242–255.
Nordhausen, B., & Langley, P. (1990). An Integrated Approach to Empirical Discovery. in: J. Shrager & P. Langley eds. Computational Models of Scientific Discovery and Theory Formation, Morgan Kaufmann Publishers, San Mateo, CA, 97–128.
Rose, D. (1989) Using Domain Knowledge to Aid Scientific Theory Revision. Proceedings of the Sixth Int. Workshop on Machine Learning, Morgan Kaufmann Publishers, San Mateo, CA, 272–277
Sleeman, D.H., Stacey, M.K., Edwards, P., & Gray, N.A.B. (1989) An Architecture for Theory-Driven Scientific Discovery, Proceedings of EWSL-89.
Stefanski P. & Żytkow Jan M. (1989) A Multisearch Approach to Sequence Prediction, in: Ras Z. ed. Methodologies for Intelligent Systems 4, New York, NY: Elsevier, 359–366.
Wrobel, S. (1989) Demand-driven Concept Formation. In Morik K. ed. Knowledge Representation and Organization in Machine Learning, Springer-Verlag, Berlin, 289–319.
Żytkow, J.M. (1987) Combining many searches in the FAHRENHEIT discovery system. Proceedings of Fourth International Workshop on Machine Learning. Los Altos, CA: Morgan Kaufmann, 281–287.
Żytkow, J.M. (1990) Deriving basic laws by analysis of processes and equations, in: J. Shrager & P. Langley eds. Computational Models of Scientific Discovery and Theory Formation. Morgan Kaufmann Publishers, San Mateo, CA, 129–156.
Żytkow, J. & Baker, J. (1991) Interactive Mining of Regularities in Databases, To be published in: Piatetsky-Shapiro, G. and Frawley, W. eds. Knowledge Discovery in Databases, The AAAI Press, Menlo Park, CA.
Żytkow, J.& Lewenstam A. (1990) Analytical Chemistry: the Science of Many Models, Fresenius Journal for Analytical Chemistry, 225–233.
Żytkow, J. & Pachowicz, P. (1989) Fusion of vision and touch for spatio-temporal reasoning in learning manipulation tasks, in: Proceedings of SPIE's Advances in Intelligent Robotic Systems, 404–415.
Żytkow, J.M., Zhu, J. & Hussam, A. (1990) Automated Discovery in a Chemistry Laboratory, Proceedings of the AAAI-90, AAAI Press, 889–894.
Żytkow, J.M., Zhu, J. & Hussam, A. (1990a) Determining Repeatability and Error in Experimental Results by a Discovery System, in Ras Z. ed. Methodologies for Intelligent Systems 5, Elsevier, New York, NY, 438–445.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Żytkow, J.M., Zhu, J. (1991). Application of empirical discovery in knowledge acquisition. In: Kodratoff, Y. (eds) Machine Learning — EWSL-91. EWSL 1991. Lecture Notes in Computer Science, vol 482. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0017007
Download citation
DOI: https://doi.org/10.1007/BFb0017007
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53816-5
Online ISBN: 978-3-540-46308-5
eBook Packages: Springer Book Archive