Machine Learning

Machine Learning

Machine learning is the study of algorithms and systems for computers to learn from data to make predictions or take actions. Our current research projects in machine learning focus on probabilistic graphical models, time-series models, deep neural networks, generative models, active learning, kernel methods, clustering, robust learning, manifold learning, and Gaussian processes. We also combine machine learning with optimization methods for not only investigating the fundamental properties of machine learning models but also handling expensive and noisy optimization problems. As the foundations of artificial intelligence, machine learning is broadly applied in computer vision, natural language processing, computer graphics, multimedia information retrieval, software engineering, cognitive science and bioinformatics. Machine learning systems are also deployed in engineering fields, such as car crash simulations and telecommunication system design.

ml1

Topics

  • Machine learning foundations
    • Learning theory
    • Machine learning optimization
    • Privacy of machine learning
    • Security of machine learning
    • Machine reasoning and causality
    • Machine learning systems
  • Machine learning models
    • Deep neural networks
    • Discriminative models
    • Generative models
    • Time-series models
    • Spatial models
    • Probabilistic models
  • Machine learning algorithms
    • Reinforcement learning
    • Unsupervised and semi-supervised learning
    • Active learning
    • Meta learning
    • Bayesian learning and Gaussian process
    • Clustering
    • Kernel method
    • Manifold learning
  • Machine learning applications
    • Computer vision
    • Natural language processing
    • Bioinformatics
    • Chemioinformatics
    • Robotics
    • Information retrieval
    • Intelligent control

Faculty

Research Centres

Courses