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...

Cijeli opis

Bibliografski detalji
Izdano u:Machine learning. 59, 1-2 (2005).
Glavni autor: Bshouty, Nader H.
Format: Članak
Jezik:engleski
Teme: