Výsledky vyhledávání - "Bshouty, N.H."

Autor: Costa Florêncio, C., Verwer, S., Bshouty, N.H., Stolz, G., Vayatis, N., Zeugmann, T.

Publikováno v: Algorithmic Learning Theory: 23rd International Conference, ALT 2012, Lyon, France, October 29-31 2012: proceedings, 81-95
STARTPAGE=81;ENDPAGE=95;TITLE=Algorithmic Learning Theory
Lecture Notes in Computer Science ISBN: 9783642341052
ALT
Bshouty, N.; Stoltz, G. (ed.), Algorithmic Learning Theory : 23rd International Conference, ALT 2012, Lyon, France, October 29-31, 2012. Proceedings, pp. 81-95
Lecture Notes in Computer Science ; 7568, 81-95. Berlin : Springer
STARTPAGE=81;ENDPAGE=95;TITLE=Lecture Notes in Computer Science ; 7568

This paper is concerned with the problem of supervised learning of deterministic finite state automata, in the technical sense of identification in the limit from complete data, by finding a minimal DFA consistent with the data (regular inference).We

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::86d68c2e5f9f30e20c8daf2cb2e8c880
https://dare.uva.nl/personal/pure/en/publications/regular-inference-as-vertex-coloring(4c0ae5a3-3107-427e-893e-a1925b05e49a).html

Zobrazit plný text záznamu

Robust Reductions from Ranking to Classification

Autor: Balcan, M.F., Bansal, N., Beygelzimer, A., Coppersmith, D., Langford, J., Sorkin, G.B., Bshouty, N.H., Gentile, C.

Publikováno v: Learning Theory ISBN: 9783540729259
COLT
Learning theory (20th Annual Conference, COLT 2007, San Diego CA, USA, June 13–15, 2007. Proceedings), 604-619
STARTPAGE=604;ENDPAGE=619;TITLE=Learning theory (20th Annual Conference, COLT 2007, San Diego CA, USA, June 13–15, 2007. Proceedings)

We reduce ranking, as measured by the Area Under the Receiver Operating Characteristic Curve (AUC), to binary classification. The core theorem shows that a binary classification regret of r on the induced binary problem implies an AUC regret of at mo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d8735d51bb5adaa5a65aa0c79c36c81
https://doi.org/10.1007/978-3-540-72927-3_43

Zobrazit plný text záznamu

Minimax bounds for active learning

Autor: Castro, R.M., Nowak, R., Bshouty, N.H., Gentile, C.

Publikováno v: Learning Theory ISBN: 9783540729259
COLT
Proceedings of the 20th Annual Conference on Learning Theory (COLT 2007), 13-15 June 2007, San Diego CA, USA, 5-19
STARTPAGE=5;ENDPAGE=19;TITLE=Proceedings of the 20th Annual Conference on Learning Theory (COLT 2007), 13-15 June 2007, San Diego CA, USA

This paper aims to shed light on achievable limits in active learning. Using minimax analysis techniques, we study the achievable rates of classification error convergence for broad classes of distributions characterized by decision boundary regulari

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0591a877e348f7b5adfa5f600a361e20
https://doi.org/10.1007/978-3-540-72927-3_3

Zobrazit plný text záznamu

Recent developments in pattern mining

Autor: Calders, T.G.K., Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T.

Publikováno v: Discovery Science ISBN: 9783642334917
Algorithmic Learning Theory (23rd International Conference, ALT 2012, Lyon, France, October 29-31, 2012. Proceedings), 34-34
STARTPAGE=34;ENDPAGE=34;TITLE=Algorithmic Learning Theory (23rd International Conference, ALT 2012, Lyon, France, October 29-31, 2012. Proceedings)
Lecture Notes in Computer Science ISBN: 9783642341052
Discovery Science
Discovery Science (15th International Conference, DS 2012, Lyon, France, October 29-31, 2012. Proceedings), 2-2
STARTPAGE=2;ENDPAGE=2;TITLE=Discovery Science (15th International Conference, DS 2012, Lyon, France, October 29-31, 2012. Proceedings)

Pattern Mining is one of the most researched topics in the data mining community. Literally hundreds of algorithms for efficiently enumerating all frequent itemsets have been proposed. These exhaustive algorithms, however, all suffer from the pattern

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6abcf2fc281d01789219c8699919c490
https://doi.org/10.1007/978-3-642-34106-9_5

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání