| |
Learning to learn from small data in the era of big data
|
Speaker (s):
Qianru SUN
Research Fellow,
NExT++ Lab,
National University of Singapore
|
|
Date:
Time:
Venue:
|
|
May 22, 2019, Wednesday
10:00am - 11:00am
Meeting Room 4.4, Level 4
School of Information Systems
Singapore Management University
80 Stamford Road
Singapore 178902
|
|
ABSTRACT
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, I 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, I 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.
About the Speaker
Dr. Qianru Sun is a research fellow working with Prof. Tat-Seng Chua and leads the computer vision group in the NExT++ Lab at the National University of Singapore, since Apr 2018. Before this, she held the Lise Meitner Award Fellowship and was a post-doctoral researcher working with Prof.Dr. Bernt Schiele and Dr. Mario Fritz at the Max-Planck Institute for Informatics (MPII) for two years. She now has a visiting researcher position at MPII. In Jan 2016, she obtained her Ph.D. degree from Peking University, and her thesis was advised by Prof. Hong Liu. From Sep 2014 to Jan 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. Specific topics include image recognition, conditional image generation, meta-learning, and transfer learning.
|
