We show that the class of monotone 2O( √ log n)-term DNF formulae can be PAC learned in polynomial time under the uniform distribution from random examples only. This is an expo...
This work addresses the problem of efficiently learning action schemas using a bounded number of samples (interactions with the environment). We consider schemas in two languages-...
We extend the classical single-task active learning (AL) approach. In the multi-task active learning (MTAL) paradigm, we select examples for several annotation tasks rather than f...
Roi Reichart, Katrin Tomanek, Udo Hahn, Ari Rappop...
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
The paper evaluates the eectiveness of learning for speeding up the solution of constraint satisfaction problems. It extends previous work (Dechter 1990) by introducing a new and ...