zbMATH — the first resource for mathematics

First-order \(jk\)-clausal theories are PAC-learnable. (English) Zbl 0938.68773

68T05 Learning and adaptive systems in artificial intelligence
68Q45 Formal languages and automata
Full Text: DOI
[1] H. Adé, L. De Raedt and M. Bruynooghe, Declarative bias for bottom-up ILP systems, Mach. Learn. (submitted).
[2] Bergadano, F.: Towards an inductive logic programming language. Technical report deliverable TO1, ESPRIT project no. 6020 ILP (1993)
[3] Blumer, A.; Ehrenfeucht, A.; Haussler, D.; Warmuth, M.: Learnability and the vapnik-chervonenkis dimension. J. ACM 36, No. 4, 929-965 (1989) · Zbl 0697.68079 · doi:10.1145/76359.76371
[4] Cohen, W. W.: PAC-learning a restricted class of recursive logic programs. Proceedings AAAI-93, 86-92 (1993)
[5] Cohen, W. W.: Learnability of restricted logic programs. Proceedings third international workshop on inductive logic programming (ILP’93), 41-71 (1993)
[6] Cohen, W. W.: Grammatically biased learning: learning logic programs using an explicit antecedent description language. Artif. intell. 68, No. 2, 303-366 (1994) · Zbl 0942.68656 · doi:10.1016/0004-3702(94)90070-1
[7] De Raedt, L.; Bruynooghe, M.: A theory of clausal discovery. Proceedings IJCAI-93, 1058-1063 (1993)
[8] De Raedt, L.; Lavrač, N.: The many faces of inductive logic programming. Proceedings seventh international symposium on methodologies for intelligent systems, 435-449 (1993)
[9] Džeroski, S.; Muggleton, S.; Russell, S.: PAC-learnability of determinate logic programs. Proceedings fifth ACM workshop on computational learning theory, 128-135 (1992)
[10] Džeroski, S.; Muggleton, S.; Russell, S.: Learnability of constrained logic programs. Proceedings sixth European conference on machine learning, 342-347 (1993)
[11] Flach, P. A.: A framework for inductive logic programming. Inductive logic programming, 193-211 (1992)
[12] Helft, N.: Induction as nonmonotonic inference. Proceedings first international conference on principles of knowledge representation and reasoning, 149-156 (1989) · Zbl 0748.03018
[13] Kietz, J. U.: Some lower bounds for the computational complexity of inductive logic programming. Proceedings sixth European conference on machine learning, 115-123 (1993)
[14] Kietz, J. U.; Džeroski, S.: Inductive logic programming and learnability. SIGART bull. 5, No. 1, 22-32 (1994)
[15] Kietz, J. U.; Wrobel, S.: Controlling the complexity of learning through syntactic and task-oriented models. Inductive logic programming, 107-126 (1992)
[16] Lloyd, J. W.: 2nd ed.foundations of logic programming. Foundations of logic programming (1987)
[17] Muggleton, S. H.: Inductive logic programming. (1992) · Zbl 0838.68093
[18] S.H. Muggleton and L. De Raedt, Inductive logic programming: theory and methods, J. Logic Programm. (to appear). · Zbl 0816.68043 · doi:10.1016/0743-1066(94)90035-3
[19] Muggleton, S. H.; Feng, C.: Efficient induction of logic programs. Proceedings first conference on algorithmic learning theory, 368-381 (1990)
[20] Natarajan, B. K.: Machine learning: A theoretical approach. (1991) · Zbl 0722.68093
[21] Page, C. D.: Anti-unification in constraint logics: foundations and applications to learnability in first-order logic, to speed-up learning and to deduction. Ph.d. thesis, report no. UICDCS-R-93-1820 (1993)
[22] Page, C. D.; Frisch, A. M.: Generalization and learnability: a case study of constrained atoms. Inductive logic programming (1992)
[23] Quinlan, J. R.: Learning logical definitions from relations. Mach learn. 5, No. 3, 239-266 (1990)
[24] Rouveirol, C.: Extensions of inversion of resolution applied to theory completion. Inductive logic programming (1992)
[25] Rouveirol, C.: Flattening and saturation: two representation changes for generalization. Mach learn. 14, 219-232 (1994) · Zbl 0804.68024 · doi:10.1023/A:1022678217288
[26] Shapiro, E. Y.: Algorithmic program debugging. (1983) · Zbl 0589.68003
[27] Valiant, L.: A theory of the learnable. Commun. ACM 27, No. 11, 1134-1142 (1984) · Zbl 0587.68077 · doi:10.1145/1968.1972
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.