Teaching
Courses taught at least in part by members of the Deep Learning Research Group:
Uncover the fundamentals of neural network-based deep learning. In this course you will learn the state-of-the-art methods for classification, regression, and generative modelling, giving you the building blocks for designing your own chatbots as well as image and video generation.
This course teaches the ideas, algorithms and techniques of probabilistic machine learning. Topics include Bayesian inference, discriminative and generative classifiers, the EM algorithm, Gaussian processes, Markov Chain Monte Carlo, hidden Markov models, belief nets and other graphical models, and causal modelling.
This course addresses several current topics in artificial intelligence. Possible topics include Reinforcement Learning, AI for robotics, AI in games, Intelligent image analysis, AI and optimisation, AI Planning.
Computer vision and image processing has a wide range of real-world applications, such as automated vehicles and face recognition. This course addresses key AI techniques, tasks, and applications in this area. The course covers a range of topics, starting from the basics of image pre-processing and data augmentation to recent deep learning techniques, addressing tasks such as edge detection, image segmentation, and image classification. Various applications of relevant techniques will also be introduced.
This course teaches fundamental concepts and mathematical techniques that underlie much of machine learning (ML). Topics include an introduction to learning theory, optimisation for ML, unsupervised learning, learning with latent variables, generative models, kernels, aspects of information theory, deep learning, continual/online learning, transfer learning, and anomaly detection. The course will also explore the connections between ML and cognitive science.
A capstone project to construct a solution to an AI task. The project may be an individual or a group project.
