Learning intersection-closed classes with signatures

Theoretical Computer Science

Volumn 382, Issue 3, 2007, Pages 209-220

  Bulatov, Andrei ^a   Chen, Hubie ^b   Dalmau, Víctor ^b  

^a SIMON FRASER UNIVERSITY   (Canada)

^b UNIVERSITAT POMPEU FABRA   (Spain)

Author keywords

Closure algorithm; Computational learning; Polymorphism; Quantified formulas

Indexed keywords

COMPUTATIONAL METHODS; ENCODING (SYMBOLS); LEARNING ALGORITHMS; POLYMORPHISM; QUERY PROCESSING;

CLOSURE ALGORITHMS; COMPUTATIONAL LEARNING; QUANTIFIED FORMULAS;

LEARNING SYSTEMS;

EID: 34547840266     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.tcs.2007.03.039     Document Type: Article

References (17)

1. Angluin D. Queries and concept learning. Machine Learning 2 (1988) 319-342
2. P. Auer, N. Cesa-Bianchi, On-line learning with malicious noise and the closure algorithm, Annals of Mathematics and Artificial Intelligence 23 (1-2) 83-99
3. Börner F., Bulatov A.A., Jeavons P.G., and Krokhin A.A. Quantified constraints and surjective polymorphisms. Proceedings of 17th International Workshop Computer Science Logic. CSL'03. Lecture Notes in Computer Science vol. 2803 (2003), Springer-Verlag 58-70
4. N. Bshouty, J. Jackson, C. Tamon, Exploiring learnability between exact and PAC, in: 15th Annual ACM Conference on Computational Learning Theory, COLT'02, 2002, pp. 244-254
5. H. Chen, The computational complexity of quantified constraint satisfaction, Ph.D. Thesis, Cornell University, 2004
6. Chen H., and Dalmau V. From pebble games to tractability: An ambidextrous consistency algorithm for quantified constraint satisfaction. Computer Science Logic (2005)
7. H. Chen, Quantified constraint satisfaction, maximal constraint languages, and symmetric polymorphisms, in: 22nd International Symposium on Theoretical Aspects of Computer Science, STACS, 2005
8. Dalmau V. A Dichotomy theorem for learning quantified Boolean formulas. Machine Learning 35 3 (1999) 207-224
9. Dalmau V., and Jeavons P. Learnability of quantified formulas. Theoretical Computer Science 306 (2003) 485-511
10. Denecke K., Erne M., and Wismath S.L. Galois Connections and Applications (2003), Kluwer Academic Publishers
11. D. Haussler, N. Littlestone, M. Warmuth, Predicting {0,1}-functions on randomly drawn points, Information and Computation 115 (2) 248-292
12. D. Hembold, R. Sloan, M. Warmuth, Learning nested differences of intersection-closed concept classes, Machine Learning 5 165-196
13. D. Hembold, R. Sloan, M. Warmuth, Learning integer lattices, SIAM Journal on Computing 21 (2) 240-266
14. Jeavons P., Cohen D., and Cooper M.C. Constraints, consistency and closure. Artificial Intelligence 101 (1998) 251-265
15. N. Littlestone, Learning quickly when irrelevant atributes abound: A new linear threshold algorithm, Machine Learning
16. B.K. Natarajan, On learning Boolean functions, in: Proceedings of the Nineteenth Annual ACM Symposium on Theory of Computing, 1987
17. Valiant L. A theory of the learnable. Communications of the ACM 27 11 (1984) 1134-1142