论文信息 - Learning monotone log-term DNF formulas

Learning monotone log-term DNF formulas

Based on the uniform distribution PAC learning model, the learnability for monotone disjunctive normal form formulas with at most <italic>O</italic>(log<italic>n</italic>) terms (<italic>O</italic>(log<italic>n</italic>)-term MDNF) is investigated. Using the technique of restriction, an algorithm that learns <italic>O</italic>(log<italic>n</italic>)-term MDNF in polynomial time is given.

Akira Maruoka | Yoshifumi Sakai

[1] Karsten A. Verbeurgt. Learning DNF under the uniform distribution in quasi-polynomial time , 1990, COLT '90.

[2] Leslie G. Valiant,et al. Computational limitations on learning from examples , 1988, JACM.

[3] Michele Flammini,et al. Learning DNF formulae under classes of probability distributions , 1992, COLT '92.

[4] Marco Protasi,et al. On the Learnability of DNF Formulae , 1988, ICALP.

[5] Leslie G. Valiant,et al. On the learnability of Boolean formulae , 1987, STOC.

[6] Leslie G. Valiant,et al. A theory of the learnable , 1984, STOC '84.

[7] Akira Maruoka,et al. A learning algorithm for monotone $k$-term DNF , 1990 .

[8] Akira Maruoka,et al. Learning k-Term Monotone Boolean Formulae , 1992, ALT.

[9] Qian-Ping Gu,et al. Learning Monotone Boolean Functions by Uniformly Distributed Examples , 1992, SIAM J. Comput..