Intelligent Systems: Probabilistic & Deep Learning - COM00049H

«Back to module search

  • Department: Computer Science
  • Credit value: 20 credits
  • Credit level: H
  • Academic year of delivery: 2025-26

Module summary

PADL-H: Probabilistic & Deep Learning

Related modules

Pre-requisite modules

Co-requisite modules

  • None

Prohibited combinations

  • None

Additional information

Pre-Requisite knowledge - Understanding of the theory and practice of Machine Learning. For undergraduates this is covered in intelligent systems modules (for example, INT2 -  Intelligent Systems 2: Machine Learning & Optimisation COM00024I or IMLO - Intelligent Systems: Machine Learning & Optimisation COM00026I).

 

Elective Pre-Requisites

These pre-requisites only apply to students taking this module as an elective.

A Level Maths or Equivalent plus good understanding of the theory and practice of machine learning.

Module will run

Occurrence Teaching period
A Semester 2 2025-26

Module aims

This module builds on the basic machine learning covered previously in the programme, and takes students up to state of the art methods in modern deep learning. It introduces probabilistic methods, where we can reason about uncertainty, and deep learning based methods, where neural networks with many layers prove to be the most powerful general model for learning. We will see a range of methods and architectures for classification and regression problems, unsupervised generative models and the mathematics that underlies these techniques. We will cover both theory and practicalities: how are these ideas actually implemented in a modern machine learning library like PyTorch?

Module learning outcomes

  • Explain the probabilistic basis of machine learning

  • Demonstrate a working knowledge of manifold embedding and kernel methods

  • Apply a range of Bayesian methods for regression, classification and clustering

  • Be familiar with the main deep learning architectures

  • Demonstrate the optimisation process and different variants (i.e. gradient descent, stochastic algorithms, ADAM)

Indicative assessment

Task % of module mark
Essay/coursework 100

Special assessment rules

None

Indicative reassessment

Task % of module mark
Essay/coursework 100

Module feedback

Feedback is provided through work in practical sessions, and after the final assessment as per normal University guidelines

Indicative reading

Solomon, Justin. Numerical Algorithms. AK Peters/CRC Press, 2015