DESCRIPTION
Data plays a vital role in AI. One of the most impactful works, such as the GPT series, demonstrates the power of ultra-large-scale and high-quality data. However, training on such data is unaffordable for most researchers. Dataset Distillation (DD) aims to synthesize small but informative datasets that achieve comparable results as training on the original large datasets. Over the past few years, this field has attracted hundreds of papers across top-tier computer vision and machine learning conferences.
DETAILS
Course type: Invited lecture (online delivery)
Duration: 1 hour
Level: PhD
Institution of lecturer: Multimedia Laboratory, The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto
LECTURER
Dr. Konstantinos N. Plataniotis
Konstantinos N. Plataniotis received his B.Eng. degree in Computer Engineering from the University of Patras, Greece, followed by an M.S. and Ph.D. in Electrical Engineering from the Florida Institute of Technology in Melbourne, Florida. He is presently a Professor at The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Canada, where he directs the Multimedia Laboratory. He has held the Bell Canada Endowed Chair in Multimedia since 2014. Dr. Plataniotis is a registered professional engineer in Ontario and a Fellow of IEEE, the Engineering Institute of Canada, and the Canadian Academy of Engineering/ L’Academie Canadienne Du Genie. His primary research areas include image/signal processing, machine learning and adaptive learning systems, visual data analysis, multimedia and knowledge media, and affective computing.