In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy
will defend his dissertation proposal
Towards Improving Single Label and Hierarchical Multi-Label Classifications
Teaching computer to do what humans can do is the ultimate goal of artificial intelligence. In the territory of artificial intelligence, classification is the most fundamental and important topic in machine learning, data mining, and pattern recognition. Humans can unconsciously distinguish different objects or patterns and classify them. However, it is not easy to tell computer program to do the same. To this end, different classification algorithms have been developed and applied to different domains, such as computer vision, natural language processing, speech recognition, genetic engineering, financial market and so on. Therefore, improving the performance of classification algorithms is crucially important for all these applications.
The goal of this research is to develop new classification algorithms that increase the performance of single label classification for visual recognition and hierarchical multi-label classification. The specific objectives in single label classification are to: (i) overcome the challenge of increasing deep neural network size; (ii) overcome the challenge of occlusion in 2D-2D face recognition; (iii) overcome the challenge of distortion of geometric image in 2D-3D and 3D-3D face recognition. The specific objectives in hierarchical multi-label classification are to (i) take advantage of the complex label correlations in class hierarchy; (ii) learn the correlations between face traits in 2D-2D face recognition. The proposed algorithms were evaluated on miscellaneous datasets and achieved significant improvements when comparing with previous baseline methods.
Date: Tuesday, January 10, 2017
Time: 9:00 AM
Place: HBS 317
Advisor: Dr. Ioannis A. Kakadiaris
Faculty, students, and the general public are invited.