One-Shot Learning: A Crucial Learning Paradigm Towards Human-like Learning

Assistant Professor Fang Yuan

Singapore Management University

Project Description

With the increasing popularity of applying machine learning for various artificial intelligence (AI) problems, a plethora of machine learning techniques are being developed. However, a critical limitation of conventional machine learning paradigms arises from the scarcity and expense of (labelled) data as popular deep learning methods often have millions of parameters and require thousands (if not millions) of samples to train an effective model. In this aspect, machine intelligence is considered inferior to human intelligence, as humans have the ability to learn rapidly from very limited data. This project explores new approaches to investigate the fundamental research problem of learning from small (labelled) data, called one-shot learning or few-shot learning, and will develop new algorithms and techniques to devise one-shot learning machines with human-like learning capabilities. The overall objective of this project is advance AI research – both in bringing AI closer to human intelligence and solving real-world problems.

Research Technical Area

Machine learning

Benefit to the society

The research on one-shot learning unlocks potential opportunities for further application in areas such as visual image recognition, healthcare analytics and cybersecurity intelligence etc. In addition to building capability and developing AI fundamentals, this development is also an enabling factor as Singapore pushes for the Smart Nation initiative.

Team's Principal Investigator

Assistant Professor Fang Yuan
School of Information Systems
Singapore Management University

Introduction of the Principal Investigator

The PI is an Assistant Professor of Information Systems at Singapore Management University, School of Information Systems. His research interests include (a) Data Analytics, (b) Machine Learning on Graphs and (c) Web and Social Media Mining. The PI obtained his PhD from University of Illinois at Urbana Champaign in 2014.

Recent Notable Awards

  • Best Paper Collection, Special Issue on VLDB ’13 best papers

Team

Co-Principal Investigator

Assoc. Prof. Steven Hoi

Singapore Management University

Research Areas:

  1. Machine learning
  2. Computer vision

Collaborators

Hady Wirawan Lauw, Singapore Management University
– Kun Zhang, Carnegie Mellon University