Towards Artificial General Intelligence with Heterogeneous Meta-Learning

Project Description

Human intelligence is remarkable in terms of generalization. A human has outstanding capability to generalize prior knowledge to a novel task with somewhat different goal or context, using little data and minimal effort. This strong generalization capability is one of the major differences between human intelligence and today’s mainstream AI systems which focus on narrow AI.

In this project, we propose, formalize, explore new approaches and create new benchmark datasets for Heterogeneous Meta-Learning with the goal of achieving generalization performance closer to human intelligence. We have identified critical research gaps pertaining to meta-learning of heterogeneous tasks, and will develop new methods to address these gaps in the project.

Research Technical Area

  • Machine Learning
  • AI

Benefits to the society

If successful, our research will advance fundamentals towards Artificial General Intelligence (AGI), propel generalization performance of an AI system to the next level, enable a new type of artificial agent that could learn a variety of tasks with minimal data/computation overhead, and make important economical and societal impacts in many sectors where AI is applied.

Project’s Publications

Team’s Principal Investigator

Ngai-Man (Man) CHEUNG

Singapore University of Technology and Design (SUTD)

Ngai-Man (Man) CHEUNG is an Associate Professor with Singapore University of Technology and Design (SUTD). He receives his Ph.D. degree in Electrical Engineering from University of Southern California (USC), Los Angeles, CA. His Ph.D. research focused on image and video coding, and the work was supported in part by NASA-JPL. He was a postdoctoral researcher with the Image, Video and Multimedia Systems group at Stanford University, Stanford, CA. His research has resulted in 14 U.S. patents granted with several pending. Two of his inventions have been licensed to companies. One of his research results has led to a SUTD spinoff on AI for wound care. His research has also been featured in the National Artificial Intelligence Strategy.

Recent Notable Awards

He has received several research recognitions including the following:

  • Best Paper Finalist at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019
  • Finalist of Super AI Leader (SAIL) Award, World AI Conference (WAIC) 2019, Shanghai, China

The Team


Prof. Alexander BINDER, University of Oslo
Research Focus: Machine Learning, AI, Computer Vision

Prof. Alex KOT, Nanyang Technological University
Research Focus: Machine Learning, AI, Computer Vision