In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy
will defend his dissertation
Towards Improving Single Label and Hierarchical Multi-Label Classification
Teaching computer to do what humans can do is the ultimate goal of artificial intelligence. In the area 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, and apply the developed algorithms in the UR2D system. The specific objectives in single label classification are to: (i) overcome the challenge of increasing deep neural network depth; (ii) overcome the challenge of occlusion in 2D-2D face recognition; (iii) overcome the challenge of using local attribute features in 2D-2D face recognition. The specific objective in hierarchical multi-label classification is to take advantage of the complex label correlations in class hierarchy. The proposed algorithms were evaluated on miscellaneous datasets and achieved significant improvements when comparing with previous baseline methods.
Date: Wednesday, October 25, 2017
Time: 10:15 AM - 12:15 PM
Place: HBS 317
Advisor: Dr. Ioannis A. Kakadiaris
Faculty, students, and the general public are invited.