A new abstract combinatorial dimension for exact learning via queries

Journal of Computer and System Sciences

Volumn 64, Issue 1, 2002, Pages 2-21

  Balcázar, José L ^a   Castro, Jorge ^a   Guijarro, David ^b  

^a UNIVERSITAT POLITÈCNICA DE CATALUNYA   (Spain)

^b Mannes Technology Consulting   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

BOOLEAN FUNCTIONS; COMPUTATIONAL COMPLEXITY; LEARNING ALGORITHMS; MATHEMATICAL MODELS; POLYNOMIALS; SET THEORY;

QUERY LEARNING MODELS;

QUERY LANGUAGES;

EID: 0036476999     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1006/jcss.2001.1794     Document Type: Article

References (20)

1. On the learnability of disjunctive normal form formulas
2. Queries and concept learning
3. Negative results for equivalence queries
4. The complexity of exactly learning algebraic concepts
5. Exact learning via teaching assistants
6. The consistency dimension and distribution-dependent learning from queries
7. Learnability and the Vapnik-Chervonenkis dimension
8. Oracles and queries that are sufficient for exact learning
9. Learning nearly monotone k-term dnf
10. On the power of equivalence queries
11. On the complexity of teaching
12. Learning from examples with unspecified attribute values
13. Exact learning when irrelevant variables abound
14. Uniform characterization of polynomial-query learnabilities
15. Generalized teaching dimension and the query complexity of learning
16. Learning read-once formulas using membership queries
17. How many queries are needed to learn?
18. On the complexity of learning from counterexamples
19. On the complexity of learning from counterexamples and membership queries
20. A framework for polynomial time query learnability