论文信息 - An Improved Inductive Learning Algorithm with a Preanalysis of Data

An Improved Inductive Learning Algorithm with a Preanalysis of Data

We propose an improved inductive learning procedure, IPI, to derive classification rules from examples. A preanalysis of data is included which assigns higher weights to those values of the attributes which occur more often in the positive than in the negative examples. The inductive learning problem is represented as a covering problem in integer programming which is solved by a modified greedy algorithm. The results are very encouraging, and are shown for a well-known M3 (Monk's) problem.

Janusz Kacprzyk | Grazyna Szkatula

[1] G. Nemhauser,et al. Integer Programming , 2020 .

[2] Ryszard S. Michalski,et al. A Theory and Methodology of Inductive Learning , 1983, Artificial Intelligence.

[3] Sebastian Thrun,et al. The MONK''s Problems-A Performance Comparison of Different Learning Algorithms, CMU-CS-91-197, Sch , 1991 .

[4] Janusz Kacprzyk,et al. MACHINE LEARNING FROM EXAMPLES UNDER ERRORS IN DATA , 1995 .

[5] Ronald R. Yager,et al. Uncertainty in Knowledge Bases , 1990, Lecture Notes in Computer Science.

[6] Ryszard S. Michalski,et al. Discovering Classification Rules Using variable-Valued Logic System VL1 , 1973, IJCAI.

[7] Nada Lavrac,et al. The Multi-Purpose Incremental Learning System AQ15 and Its Testing Application to Three Medical Domains , 1986, AAAI.

[8] Janusz Kacprzyk,et al. An algorithm for learning from erroneous and incorrigible examples , 1996 .

[9] Grazyna Szkatula,et al. Inductive learning supported by integer programming , 1991 .

[10] Janusz Kacprzyk,et al. Fuzzy logic with linguistic quantifiers in inductive learning , 1992 .

[11] Janusz Kacprzyk,et al. Inductive Learning From Incomplete and Imprecise Examples , 1990, IPMU.

[12] L. Zadeh,et al. Fuzzy Logic for the Management of Uncertainty , 1992 .