S. Matar. Learning with minimal number of queries. Master's thesis, University of Alberta, Canada, 1993. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
On Learning Read-k-Satisfy-j DNF - Aizenstein, Blum, Khardon.. (1998) (Correct)
....queries and produce O(sm 2 m 3 (kjq ) terms. This immediately gives a bound on the number of negative counterexamples. Hence, the number of equivalence queries is O(sm 2 m 3 (kjq ) Note that just by the Read k property of F we have s kn. A tighter bound of s = O( jn) is given by [Mat93] Claim 18 Let ffi 0 be a constant and kj = O( log log n ) The algorithm Learn RkSj runs in time poly(n) and finds a function logically equivalent to F with probability at least 1 Gamma ffi. Proof: By Claim 17, the algorithm succeeds with probability at least 1 Gamma ffi . The polynomial ....
S. Matar. Learning with minimal number of queries. Master's thesis, University of Alberta, Canada, 1993.
On Learning Read-k-Satisfy-j DNF - Aizenstein, Blum, Khardon.. (1996) (Correct)
....O(sm 2 m 3 (kjq 2 ) 4kj ) terms. This immediately gives a bound on the number of negative counterexamples. Hence, the number of equivalence queries is O(sm 2 m 3 (kjq 2 ) 4kj ) Note that just by the Read k property of F we have s kn. A tighter bound of s = O( p k 2 jn) is given by [Mat93] Claim 18 Let ffi 0 be a constant and kj = O( log n log log n ) The algorithm Learn RkSj runs in time poly(n) and finds a function logically equivalent to F with probability at least 1 Gamma ffi. Proof: By Claim 17, the algorithm succeeds with probability at least 1 Gamma ffi . The ....
S. Matar. Learning with minimal number of queries. Master's thesis, University of Alberta, Canada, 1993.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC