Maximizing Agreements with One-Sided Error with Applications to Heuristic Learning.

We study heuristic learnability of classes of Boolean formulas, a model proposed by Pitt and Valiant. In this type of example-based learning of a concept class C by a hypothesis class H, the learner seeks a hypothesis hisin H that agrees with all of the negative (resp. positive) examples, and a maxi...

पूर्ण विवरण

ग्रंथसूची विवरण

में प्रकाशित:	Machine learning. 59, 1-2 (2005).
मुख्य लेखक:	Bshouty, Nader H.
स्वरूप:	लेख
भाषा:	English
विषय:	Maximizing agreements. Heuristic learning. Example-based learning. Agnostic learning. Boolean formulas. Approximation.