Face recognition with improved deep belief networks

Deep learning techniques have become the state-of-the-art approach for classification in artificial intelligence, and applied in many widespread subjects. Deep Belief Networks (DBNs) are one of the most successful models. DBNs consist of many layers of hidden factors along with a greedy layer-wise unsupervised learning algorithm. In our paper, we brought forward an approach to face recognition based on dropout DBNs, which made good performances on small training sets.