Abstract
The knowledge acquisition process of many Machine Learning approaches is idealized with respect to the exclusion of noisy data, the applicability of backtracking methods, or the arrangement of training examples by a teacher. This paper describes the consequence that arises if the idealization must be abandoned: the system may be led to a dead end. Some tentative ideas are presented as to how a system should react when an increasing number of counter examples arise by the developing a new “paradigm” that must be introduced contrainductively (that is, against well supported hypotheses and factual knowledge).
“Kontrainduktiv” ist nach Feyerabend (83) ein Vorgehen, bei dem Hypothesen eingefuehrt und ausgebaut werden, die gut bestaetigten Theorien und/oder Fakten widersprechen.
Dieser Aufsatz entstand im Rahmen des vom BMFT gefoerderten Projektes “Kognitive Verfahren zur Informations-Extraktion und Zusammenfassung aus Texten (KIT)” (PT 135.01). Fuer wertvolle Anregungen und die Unterstuetzung danke ich Christopher Habel und Claus-Rainer Rollinger.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Literatur
Carey, S.: “The Child as Word Learner”; In: M. Halle, J. Bresnan, G. Miller (eds.): Linguistic Theory and Psychological Reality; Cambridge, Mass. 1978
Doyle, J.: “A Truth Maintenance System” Artificial Intelligence 12(3), 1979
Emde, W. / Habel, Ch. / Rollinger, C.-R.: “Automatische Akquisition von inferentiellem Wissen” In: W. Wahlster (ed.): GWAI-82, 6th German Workshop on Artificial Intelligence; Springer Verlag, Berlin, 1982
Emde, W. / Habel, Ch. / Rollinger, C.-R.: “The Discovery of the Equator (or Concept Driven Learning)” In: Proc. IJCAI-83, Karlsruhe, 1983
Feyerabend, P.: “Wider den Methodenzwang” Suhrkamp Verlag, Frankfurt a.M., 1976, 1983
Habel, Ch.: “Referential Nets a Knowledge Structures (Some Structural and Dynamical Properties)” KIT-Report 8, TU-Berlin 1982/ Erscheint in: T. T. Ballmer (ed.): Linguistic Dynamics”, de Gruyter, 1983
Habel, Ch. / Rollinger, C.-R.: “The Machine as Concept Learner” In: Proceedings of the ECAI-82, Orsay, Frankreich, 1982
Hayes-Roth, F.: “Using Proofs and Refutations to Learn from Experience” In: Michalski / Carbonell, / Mitchell (eds.): Machine Learning; Tioga Press, Palo Alto, 1983
Kuhn, T.S.:“Die Struktur wissenschaftlicher Revolutionen” 5.Auflage, Suhrkamp Taschenbuch Verlag, Frankfurt a.M., 1981
Lakatos, I: “Beweise und Widerlegungen” Vieweg, 1979
Langley, P. / Bradshaw, G.L. / Simon, H.A.: “BACON.5: The Discovery of Conservation Laws” CIP Working Paper NO.430, Carnegie-Mellon University, 1981
Morik, K. / Rollinger, C.R.: “Partnermodellierung im Evidenzraum” Erscheint in: B. Neumann (ed.): GWAI-83, 7th German Workshop on Artificial Intelligence; Springer Verlag, Berlin, 1983
SemNet.: “Automatische Erstellung semantischer Netze” Projektabschlussbericht; TU-Berlin 1981
Shapiro, E.H.: “Inductive Inference of Theories from Facts” Yale University, Research Report 192, 1981
Smith, D.E.: FOCUSER: A Strategic Interaction Paradigm for Language Acquisition; Technical Report LCSR-TR-36, Rutgers University, 1982
Stallman, R.M. / Sussman, G.J.: “Forward Reasoning and Dependency-Directed Backtracking in a System for Computer-Aided Circuit Analysis” Artificial Intelligence 9(2), 1977
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1983 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Emde, W. (1983). Kontrainduktives Lernen von Konzepten aus Fakten. In: Neumann, B. (eds) GWAI-83. Informatik-Fachberichte, vol 76. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-69391-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-69391-5_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-12871-7
Online ISBN: 978-3-642-69391-5
eBook Packages: Springer Book Archive