Date：Aug 23rd, 2023
Time: 11:00–11:50
Place: 55N-1F-Conference Room 1
Speaker: Utku Ozbulak (Ghent University Global Campus, South Korea)
Title: An overview of self-supervised learning
Abstract: Self-supervised learning has recently emerged as a powerful paradigm for neural networks. This approach leverages unlabeled data to
pretrain neural networks, enabling them to learn meaningful representations without requiring extensive manual annotation. By capitalizing on the
inherent structure and information present in the data itself, self-supervised learning has demonstrated remarkable success in a diverse range of
problems across computer vision, natural language processing, and other domains. In this talk, I will briefly go over the recent advances in the
field and discuss how self-supervised learning enabled now-famous models like Chat-GPT and the Segment All Model (SAM).
contact：Prof.yoshimura（[email protected]）
