Pac-learning non-recursive prolog clauses

Artificial Intelligence

Volumn 79, Issue 1, 1995, Pages 1-38

  Cohen, William W ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

inductive logic programming; Machine learning; pac learning

Indexed keywords

LOGIC PROGRAMMING; PROLOG (PROGRAMMING LANGUAGE); STANDARDS;

CLAUSES; DESCRIPTION LOGICS; FUNCTION FREE CLAUSES; INDETERMINACY; INDUCTIVE LOGIC PROGRAMMING; MULTIPLE CLAUSES; PAC LEARNING; SYNTHETIC GENERALIZATIONS;

LEARNING SYSTEMS;

EID: 0029408886     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/0004-3702(94)00034-4     Document Type: Article

References (51)

1. Learning conjunctions of horn clauses
2. Learning functions of k terms
3. Classifying learnable concepts with the Vapnik-Chervonenkis dimension
4. The complexity of finite functions
5. Grammatically biased learning: learning logic programs using an explicit antecedent description language
6. Compiling knowledge into an explicit bias
7. Cryptographic limitations on learning one-clause logic programs
8. Learnability of restricted logic programs
9. A pac-learning algorithm for a restricted class of recursive logic programs
10. Rapid prototyping of ILP systems using explicit bias
11. Pac-learning nondeterminate clauses
12. Learnability of description logics
13. Pac-learnability of determinate logic programs
14. Inducing temporal fault diagnosic rules from a qualitative model
15. Learning DNF formulae under classes of probability distributions
16. Learnability of recursive, non-determinate theories: Some basic results and techniques
17. Learning from entailment: An application to propositional horn sentences
18. Learning constrained atoms
19. Learning kμ decision trees on the uniform distribution
20. Learning conjunctive concepts in structural domains
21. On the learnability of boolean formulae
22. Cryptographic limitations on learning Boolean formulae and finite automata
23. Cryptographic lower bounds on the learnability of boolean functions on the uniform distribution
24. Some computational lower bounds for the computational complexity of inductive logic programming
25. Inductive logic programming and learnability
26. Constructive induction of background knowledge
27. Drug design by machine learning the use of inductive logic programming to model the structure-activity relationships of trimethoprim analogues binding to dihydrofolate reductase
28. On learning visual concepts and DNF formulae
29. Background knowledge and declarative bias in inductive concept learning
30. Learning simple concepts under simple distributions
31. The application of inductive logic programming to finite-element mesh design
32. Inductive logic programming
33. Efficient induction of logic programs
34. Protein secondary structure prediction using logic-based machine learning
35. The utility of knowledge in inductive learning
36. Classic learning
37. Computational limitations on learning from examples
38. Reductions among prediction problems: On the difficulty of predicting automata
39. Prediction-preserving reducibility
40. A note on inductive generalization
41. Learning logical definitions from relations
42. Determinate literals in inductive logic programming
43. The strength of weak learnability
44. A theory of the learnable
45. On analytical and similarity-based classification