Quantifying inductive bias: AI learning algorithms and Valiant's learning framework

Artificial Intelligence

Volumn 36, Issue 2, 1988, Pages 177-221

  Haussler, David ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER PROGRAMMING - ALGORITHMS; SYSTEMS SCIENCE AND CYBERNETICS - LEARNING SYSTEMS;

CONJUNCTIVE CONCEPTS; INDUCTIVE BIAS; INTERNAL DISJUNCTION; LEARNING ALGORITHMS; VALIANT'S LEARNING FRAMEWORK;

ARTIFICIAL INTELLIGENCE;

EID: 0024082469     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/0004-3702(88)90002-1     Document Type: Article

References (46)

1. Queries and concept learning
2. Learning from noisy examples
3. The logic of learning: a basis for pattern recognition and improvement of performance
4. Occam's razor
5. An analytical comparison of some rule-learning programs
6. A greedy heuristic for the set covering problem
7. Geometrical and statistical properties of systems of linear inequalities with applications to pattern recognition
8. A comparative review of selected methods for learning from examples
9. Learning decision trees from random examples
10. Quantifying the inductive bias in concept learning
11. Applying Valiant's learning framework to AI concept learning problems
12. Epsilon nets and simplex range queries
13. Approximation algorithms for combinatorial problems
14. On knapsacks partitions and a new dynamic programming technique for trees
15. Learning in the presence of malicious errors
16. Recent results on Boolean concept learning
17. Inductive inference by refinement
18. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
19. A theory and methodology of inductive learning
20. Learning in the presence of background knowledge
21. The need for biases in learning generalizations
22. Generalization as search
23. Two new frameworks for learning
24. The fastest descent method for covering problems
25. On the connection between the complexity and credibility of inferred models
26. Induction of decision trees
27. A general framework for induction and a study of selective induction
28. Modeling by shortest data description
29. Learning decision-lists
30. Incremental adjustment of representations for learning
31. Learning concepts by asking questions
32. Factorization in experiment generation
33. Shift of bias for inductive concept learning
34. A theory of the learnable
35. Learning disjunctions of conjunctions
36. Computational limitations on learning from examples
37. On the uniform convergence of relative frequencies of events to their probabilities
38. Some special Vapnik-Chervonenkis classes
39. Learning structural descriptions from examples