Skip to main content
Malaya AI Research Universiti Malaya, FCSIT
Research area

Explainable / Trustworthy AI

Building interpretable, transparent, and responsible AI systems — including XAI for agents, robots, and healthcare.

All research areas View publications

Overview

This area asks what has to be true of a model before people can reasonably rely on it. Research covers interpretability methods for agents and robots, explainability in medical image analysis, model ownership and watermarking, and responsible AI practice. The centre's ACM Computing Surveys work on explainable goal-driven agents and robots sits here, as does explainable AI applied to dermoscopic image classification. In practice the area functions less as a separate subject than as a constraint the centre applies to its healthcare, robotics and language work.

Topics

  • Explainable AI
  • Interpretable machine learning
  • Responsible AI
  • Trustworthy autonomous systems
  • Healthcare AI

Researchers

4 academic members of Malaya AIR work in this area.

Related projects

Flagship Research

TrustGuard

AI applications in healthcare, federated learning, explainable AI and medical imaging.

UM Spin-off

UMCH Technology

Connected digital health bridging clinical practice and artificial intelligence, with industry collaboration.

Selected publications

Collaboration

Interested in research collaboration, technical exchange or translational opportunities related to this area?

Discuss a Collaboration