Active learning with teacher-learner mutuality

In active learning, the basic objective is to reach a desired performance of some learning algorithm with as little training instances as possible. The reason behind is that labeling of training instances may be expensive with respect to the amount of time and intellectual effort of a human annotator. We propose a new approach for active learning, called "mutual active learning", which helps the artificial intelligent learner to pose questions to his human teacher, which are as clear and as understandable as possible. Such learning appears to be more reliable and successful than basic active learning.