Bayesian, Active & Reinforcement Learning

Learning Outcomes

Subject Specific Intellectual and Research Skills

Having successfully completed this module you will be able to:

• Critically appraise the merits and shortcomings of model architectures on specific problems.
• Critical appraisal of recent scientific literature in Bayesian inference & active learning.

Subject Specific Practical Skills

Having successfully completed this module you will be able to:

• Apply existing Bayesian and active learning methods to real applications.
• Gain facility in working with Bayesian paradigm and active learning methodology in order to create and evaluate their performance and applicability in different application domains.

Knowledge and Understanding

Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:

• The key factors that have made Bayesian inference & active learning g successful for various applications.
• Underlying mathematical and algorithmic principles of Bayesian inference & active learning.

Reasoning under uncertainty

• Bayesian paradigm
• Recognising sources of uncertainty and approaches to handling them
• Maximum a posteriori estimation

Approximate inference

• Local linearisation
• Markov Chain Monte Carlo
• Sequential Monte Carlo
• Variational inference

Bayesian deep learning

• Variational autoencoders
• Weight uncertainty & Bayes by backprop

Temporal-difference learning

Active and reinforcement learning

• Uncertainty, regret and reward
• Markov decision processes
• Decision optimisation

In-depth case study (one or more taken from the following applications):

• Robot Localisation & Motion planning
• Machine listening

Spatio-temporal modelling

Teaching and learning methods

Lectures and labs

Resources & Reading list

Textbooks

David Barber (2010). Bayesian Reasoning and Machine Learning. Cambridge University Press.

David MacKay (2012). Information Theory, Inference, and Learning Algorithms. Cambridge University Press.

Kevin Murphy (2021). Probabilistic Machine Learning. MIT Press.

Summative

This is how we’ll formally assess what you have learned in this module.

Referral

This is how we’ll assess you if you don’t meet the criteria to pass this module.

Repeat

An internal repeat is where you take all of your modules again, including any you passed. An external repeat is where you only re-take the modules you failed.

Repeat Information

Repeat type: Internal & External