Information Adaptation Across Class Boundary, by Yuhong Guo, Carleton University
October 19, 2017 at 1:30 PM to 3:30 PM
|Location:||5345 Herzberg Laboratories|
Emerging data resources in the big data era have created new opportunities to break the main bottleneck of machine learning systems; namely, their reliance on human annotated training data. Generalized information adaptation provides mechanisms for exploiting freely available auxiliary data resources to reduce human effort and improve the autonomy of machine learning. In this talk, I will first briefly introduce the problem of generalized information adaptation, and then discuss a special type of information adaptation, zero-shot learning, which transfers knowledge across classes to recognize new objects. In particular, I will present zero-shot learning methodologies that exploit both text and image resources to build connections across various class categories. Promising empirical results are reported.
About the speaker
Dr. Yuhong Guo is an Associate Professor in the School of Computer Science at Carleton University and a Canada Research Chair in Machine Learning. She received her PhD in Computing Science from the University of Alberta, and has previously worked at the Australian National University and Temple University. She has served in the Senior Program Committees of AAAI-16, AAAI-17, AAAI-18, IJCAI-15, IJCAI-16, IJCAI-17, and ACML-17, and as a Program Co-chair for the Output Representation Learning workshops at NIPS-13 and NIPS-14, and the Heterogeneous Learning workshops at SDM-14 and SDM-15. Her research interests include machine learning, natural language processing, computer vision and bioinformatics. She has received a number of awards for her research, including best paper prizes at IJCAI and AAAI.
Please note attendance will be taken.