ARTIFICIAL INTELLIGENCE

As advances in machine learning have grown exponentially in recent years, artificial intelligence has become one of the fastest-moving fields in computer science. ​

From robot vacuum cleaners to machine learning augmented online shopping recommendations and search engine predictions, our work drives innovations that are now part of our everyday lives.

auto

WHAT WE DO

Image

Conduct research in various areas of artificial intelligence theory, improving existing methodology and examining real-world applications.

Image

Develop computer programs and computer-controlled robots that can execute real-world tasks.

SUB AREAS:

Computer Vision

​Decision Making & Planning

​Knowledge Representation & Reasoning

​Learning Theory

​Machine Learning

Multi-Agent Systems & Algorithmic Game Theory

Natural Language Processing

Robotics

Trustworthy AI

OUR RESEARCH PROJECTS

Recommendation Systems

KAN Min Yen

Recommendations Systems curate our news feeds, and show products for us to buy, shows to watch and music to listen to. Our work examines the use of temporal and prerequisite constraints in improving recommendation systems quality in sparse data application areas, such as module and course recommendation.

  • TRL 5
  • Knowledge Representation & Reasoning

Task Oriented Dialogue Systems

KAN Min Yen

We now use voice- and text-enabled chatbots and dialogue systems often to accomplish tasks. We examine ways to improve such systems by incorporating everyday knowledge in the form of knowledge graphs and incorporating means to adapt trained systems to new domain application areas.

  • TRL 4
  • Natural Language Processing

Algorithmic Solutions for Fair Resource Allocation

Warut SUKSOMPONG


Computational Methods for Tournament Selection

Warut SUKSOMPONG


Intelligent Modelling for Decision-Making in Critical Urban Systems - DesCartes

Abhik ROYCHOUDHURY


Learning to reason and plan with visual and linguistic inputs

LEE Wee Sun

Different subfields of AI, e.g. vision, language, reasoning, learning has been studied separately in depth. However, like the blind men and the elephant, can we truly understand the subject that way? We seek to exploit recent progress, particularly in deep learning, to effectively combine these methods within a single learning architecture. Image credit: Golden Treasury Readers: Primer.

  • Computer Vision, Decision Making & Planning, Machine Learning, Natural Language Processing

Algorithmic Inductive Bias

LEE Wee Sun

Effective deep learning methods are usually structured, e.g. convolutional neural networks. How do we design a structure for a target task? We study the use of task related algorithms. The process, called neuralizing the algorithm, unrolls the execution of the algorithm into a computation graph and replaces some graph elements with learnable approximators, capturing important information flow.

  • Machine Learning

Algorithmic fairness in machine learning

Reza SHOKRI


Auditing data privacy (in machine learning)

Reza SHOKRI


Theoretical foundations of data privacy in machine learning

Reza SHOKRI


Robustness and security in machine learning

Reza SHOKRI


Model explanations and interpretable machine learning

Reza SHOKRI


Trustworthy de-centralized (federated) learning

Reza SHOKRI


Modern methods for high-dimensional estimation and learning

Jonathan SCARLETT

Extensive research has led to a variety of powerful techniques for high-dimensional learning, with the prevailing approaches assuming low-dimensional structure such as sparsity and low-rankness. This project pursues a paradigm shift towards data-driven techniques, including the replacement of explicit modeling assumptions by implicit generative models based on deep neural networks.

  • Learning Theory, Machine Learning

Information-theoretic limits of statistical inference and learning problems

Jonathan SCARLETT

The field of information theory was introduced to understand the fundamental limits of data compression and transmission, and has shaped the design of practical communication systems for decades. This project pursues the emerging perspective that information theory is not only a theory of communication, but a far-reaching theory of data benefiting diverse inference and learning problems.

  • Learning Theory, Machine Learning

Robustness considerations in machine learning

Jonathan SCARLETT

Robustness requirements pose many of the most important unsolved challenges in modern machine learning, arising from sources of uncertainty such as mismatched models, corrupted data, and adversaries. This project seeks to better understand some of the most practically pertinent sources of uncertainty and develop new algorithms that are robust in the face of this uncertainty.

  • Learning Theory, Machine Learning

Learning with Less Data: Automated Machine Learning with Bayesian Optimization

LOW Kian Hsiang

How can the hyperparameters of a deep learning model be automatically optimized without human intervention? How did the win-rate of AlphaGo improve from 50% to 66.5%? How can the nutrients, lighting and water conditions be optimized to maximize the crop yield? Look no further: Bayesian optimization is what you need.

  • TRL 4
  • Decision Making & Planning, Machine Learning, Multi-Agent Systems & Algorithmic Game Theory, Robotics

Federated/Collaborative Machine Learning and Data Valuation

LOW Kian Hsiang, HE Bingsheng, NG See Kiong

Federated/Collaborative ML is an appealing paradigm to build improved, high-quality ML models by training on aggregated data from many parties. How then can these parties be incentivized to collaborate & share their data?

  • TRL 4
  • Decision Making & Planning, Machine Learning, Multi-Agent Systems & Algorithmic Game Theory, Trustworthy AI

OUR RESEARCH GROUPS

Jonathan Scarlett's Research Group

Jonathan SCARLETT

Our group performs research at the intersection of information theory, machine learning, and high-dimensional statistics, with ongoing areas of interest including information-theoretic limits of learning, adaptive decision-making under uncertainty, scalable algorithms for large-scale inference and learning, and robustness considerations in machine learning.

  • Learning Theory, Machine Learning

STeAdS Virtual Group

Ganesh NEELAKANTA IYER

Software Engineering and Technological Advancements for Society. A virtual group that uses Software engineering practices (Agile, DevOps and Project Mgmt) and Technological advancements (Cloud computing, Artificial Intelligence (EdgeAI, Game Theory, ML/DL/RL)) for the benefit of various aspects of society (healthcare, education, art & culture). Looking for students to build a website for STeAdS.

  • Decision Making & Planning, Machine Learning, Multi-Agent Systems & Algorithmic Game Theory

Data Privacy and Trustworthy Machine Learning Lab

Reza SHOKRI


Multi-Agent Planning, Learning, and Coordination Group (MapleCG)

LOW Kian Hsiang

Our group is multi-disciplinary: CS, math, stats, physics, eng, data science. We believe in theory & practice. Our research cover probabilistic ML (Bayesian deep learning, Gaussian process), learning with less data (autoML, Bayesian optimization, meta-learning, active learning), multi-party ML (federated/collaborative ML, privacy-preserving ML), reinforcement learning & multi-agent/robot systems.

  • Decision Making & Planning, Machine Learning, Multi-Agent Systems & Algorithmic Game Theory, Robotics, Trustworthy AI