报告题目：Learning to Learn from Small Data in the Era of Big Data
Dr. Qianru Sun is currently a research fellow working with Prof. Tat-Seng Chua at the National University of Singapore. From 2016 to 2018, she held the Lise Meitner Award Fellowship and worked with Prof. Dr. Bernt Schiele at the Max-Planck Institute for Informatics (MPII), Germany. In Jan 2016, she obtained her Ph.D. degree from Peking University, and her thesis was advised by Prof. Hong Liu. From 2014 to 2015, she was a visiting Ph.D. student advised by Prof. Tatsuya Harada at the University of Tokyo. Her research interests are computer vision and machine learning — the core fields of artificial intelligence. Specific research topics include image recognition, conditional image generation, meta-learning, and transfer learning.
A machine learning model often requires a large number of training samples for good performance. In contrast, humans can learn new concepts and master new skills faster and more efficiently from small data. For example, kids can easily tell dogs and cats apart after seeing them only a few times. A person who knows how to ride a bike can learn to ride a motorcycle fast with a little or even no demonstration. So, the question is "Can we design a machine learning model to have the same ability to learn fast and efficiently?" In this talk, Dr Sun will present my recent works on "Learning to learn from small data''. The key ideas are inspired by humans' lifelong learning mechanism that humans can successfully exploit learning experience in previous small data tasks for tackling subsequent ones. Specifically, Dr Sun will introduce my proposed algorithms -- "Learning to transfer knowledge", "Learning to generate data", and "Learning to customize and combine models", and will show some concrete results.