This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Inductive Learning in Deductive Databases
December 1993 (vol. 5 no. 6)
pp. 939-949

Most current applications of inductive learning in databases take place in the context of a single extensional relation. The authors place inductive learning in the context of a set of relations defined either extensionally or intentionally in the framework of deductive databases. LINUS, an inductive logic programming system that induces virtual relations from example positive and negative tuples and already defined relations in a deductive database, is presented. Based on the idea of transforming the problem of learning relations to attribute-value form, several attribute-value learning systems are incorporated. As the latter handle noisy data successfully, LINUS is able to learn relations from real-life noisy databases. The use of LINUS for learning virtual relations is illustrated, and a study of its performance on noisy data is presented.

[1] L. Bratko, I. Mozetic, and N. Lavrac.KARDIO: A Study in deep and qulitative Knowledge for expert Systems, MIT Press, Cambridge, MA, 1989.
[2] J. Catlett, "Peepholing: Choosing attributes efficiently for megainduction," inProc. 9th Int. Conf. Mach. Learn., Morgan Kaufmann, San Mateo, CA, 1992, pp. 49-54.
[3] B. Cestnik, I. Kononenko, and I. Bratko, "ASSISTANT 86: A knowledge elicitation tool for sophisticated users," inProgress in Machine Learning. I. Bratko and N. Lavrac, eds. Wilmslow, Sigma, 1987. pp. 31-45.
[4] P. Clark and R. Boswell, "Rule induction with CN2: Some recent improvements," inProc. 5th European Working Session on Learning, Berlin: Springer, 1991, pp. 151-163.
[5] P. Clark and T. Niblett, "The CN2 induction algorithm,"Machine Learning, vol. 3, pp. 261-283, 1989.
[6] Interactive Theory Revision: An inductive Logic Programming Approuch. London: Academic, 1992.
[7] S. Dzeroski. "Handling noise in inductive logic programming," M.Sc. thesis, Faculty of Elec. Eng. and Comp. Sci., University of Ljubljana, Slovenia, 1991.
[8] S. Dzeroski and N. Lavrac, "Learning relations from noisy examples: An empirical comparison of LINUS and FOIL," inProc. 8th Int. Workshop on Machine Learning, Morgan Kaufmann, San Mateo, CA, 1991, pp. 399-402.
[9] S. Dzeroski, B. Cestnik, and I. Petrovski, "The use of Bayesian probability estimates in rule induction," inProc. 1st Elect. Comp. Sci. Conf., Volume B, Slovenia Section IEEE, Ljubljana, 1992, pp. 155-158.
[10] W.J. Frawley, G. Piatetsky-Shapiro, and C.J. Matheus, "Knowledge Discovery in Databases: An Overview,"AI Magazine, Vol. 13, No. 3, 1992, pp. 57-70.
[11] P. Harmon, R. Maus, and W. Morrisey.Expert Systems: Tools and Applications. New York: Wiley, 1988.
[12] N. Lavrac, "Principles of knowledge acquisition in expert systems," Ph.D. Thesis, Faculty of Tech. Sci., University of Maribor, Slovenia, 1990.
[13] N. Lavrac and S. Dzeroski, "Background knowledge and declarative bias in inductive concept learning," inProc. 3rd Int. Workshop on Analogical and Inductive Inference, K. Jantke, ed. Berlin: Springer, 1992, pp. 51-71.
[14] N. Lavrac and S. Dzeroski, "Inductive learning of relations from noisy examples," inInductive Logic Programming, S. H. Muggleton, ed. London: Academic, 1992, pp. 495-516.
[15] N. Lavrac and S. Dzeroski,inductive Logic Programming: Techniques and Applications. Chichester: Ellis Horwood, 1993. TO appear.
[16] N. Lavrac, S. Dzeroski, and M. Grobelnik, "Learning nonrecursive definitions of relations with LINUS," inProc. 5th European Working Session on Learning. Berlin: Springer, 1991, pp. 265-281.
[17] N. Lavrac, S. Dzeroski, V. Pimat, and V. Krizman, "Learning rules for early diagnosis of rheumatic diseases," inProc. 3rd Scandinavian Conf. Art. Intell. Amsterdam: IOS Press, 1991, pp. 138-149.
[18] N. Lavrac, S. Dzeroski, V. Pirnat, and V. Krizman, "The use of background knowledge in learning medical diagnostic rules,"Appl. Art. Intell., 7, 1993, To appear.
[19] J.W. Lloyd,Foundations of Logic Programming, Springer-Verlag, New York, 1987.
[20] R. S. Michalski, I. Mozetic, J. Hong, and N. Lavrac, "The multi-purpose incremental learning system AQ15 and its testing application on three medical domains," inProc. National Conf. Art. Intell.San Mateo, CA: Morgan Kaufmann, 1986, pp. 1041-1045.
[21] K. Morik, K. Causse, and R. Boswell, "A common knowledge representation integrating learning tools," inProc. 1st Int. Workshop on Multistrategy Learning. Fairfax, VA: George Mason University, 1991, pp. 81-96.
[22] I. Mozetic, "NEWGEM: Program for learning from examples, technical documentation and user's guide,"Reports of Intelligent Systems Group, No. UIUCDCS-F-85-949, Dep. Comp. Sci., Univ. Illinois, Urbana-Champaign, 1985. (AlsoTechnical Report IJS-DP-4390, Jozef Stefan Institute, Ljubljana. Slovenia.)
[23] I. Mozetic, "Learning of qualitative models," inProgress in Machine Learning, I. Bratko and N. Lavrac, eds. Wilmslow: Sigma, 1987, pp. 201-217.
[24] S. H. Muggleton, ed.Inductive Logic Programming. London: Academic, 1992.
[25] S. H. Muggleton and W. Buntine, "Machine invention of first-order predicates by inverting resolution," inProc. 5th Int. Conf. Mach. Learn. San Mateo, CA: Morgan Kaufmann, 1988, pp. 339-352.
[26] S. H. Muggleton and C. Feng, "Efficient induction of logic programs, " inProc. First Conf. Algorithmic Learning Theory. Tokyo: Ohmsha, 1990, pp. 368-381.
[27] S. H. Muggleton, M. Bain, J. Hayes-Michie, and D. Michie, "An experimental comparison of human and machine learning formalisms," inProc. 6th Int. Workshop Mach. Learn. San Mateo, CA: Morgan Kaufmann, 1989, pp. 113-118.
[28] S. H. Muggleton, A. Srinivasan, and M. Bain, "Compression, significance, and accuracy," inProc 9th Int. Conf. Mach. Learn.San Mateo, CA: Morgan Kaufmann, 1992, pp. 338-347.
[29] M. Pazzani and D. Kibler, "The utility of knowledge in inductive learning,"Machine Learning, vol. 9, no. 1, pp. 57-94, 1992.
[30] J. R. Quinlan, "Induction of decision trees,"Machine Learning, vol. 1, no. 1, pp. 81-106, 1986.
[31] J. Quinlan, "Simplifying decision trees,"Int. J. Man-Machine Studies, vol. 27, pp. 221-234, 1987.
[32] J.R. Quinlan, "Learning Logical Definitions from Relations,"Machine Learning, Vol. 5, No. 3, Aug. 1990, pp. 239-266.
[33] J. R. Quinlan, "Knowledge acquisition from structured data-Using determinate literals to assist search,"IEEE Expert, vol. 6, no. 6, pp. 32-37, 1991.
[34] E. Shapiro,Algorithmic Program Debugging. Cambridge, MA: MIT Press, 1983.
[35] J. D. Ullman,Database and Knowledge-base Systems. Rockville, MD: Computer Science Press, 1988.

Index Terms:
inductive learning; deductive databases; single extensional relation; LINUS; inductive logic programming system; virtual relations; negative tuples; attribute-value form; attribute-value learning systems; noisy data; real-life noisy databases; deductive DBMS; database theory; deductive databases; learning (artificial intelligence); logic programming
Citation:
S. Dzeroski, N. Lavrac, "Inductive Learning in Deductive Databases," IEEE Transactions on Knowledge and Data Engineering, vol. 5, no. 6, pp. 939-949, Dec. 1993, doi:10.1109/69.250076
Usage of this product signifies your acceptance of the Terms of Use.