Selecting right questions with Restricted Boltzmann Machines

The problem of selecting the proper set of questions plays very important role in the domain of information retrieval, e.g., on the Internet, or about requirements during the business interview. In this work we propose a novel approach for selecting the sequence of binary questions to be asked to identify an unknown concept. This solution makes use of Restricted Boltzmann Machine (RBM) as a universal approximator of the distribution over the observable variables. The main idea of the proposed approach is to use RBM to determine transition probabilities in the evolving random process for finding the most suitable question to be selected. We evaluate the proposed approach on two reference datasets.