Intelligent Systems: Probabilistic & Deep Learning - COM00049H

«Back to module search

  • Department: Computer Science
  • Credit value: 20 credits
  • Credit level: H
  • Academic year of delivery: 2023-24

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).

 

Module will run

Occurrence Teaching period
A Semester 2 2023-24

Module aims

This module advances the IS stream by introducing the basics of machine learning, purely from an optimisation perspective. The range of topics covers linear regression (picking up where Data left off) to decision trees and a simple neural network (leading into advanced machine learning in the third year). Understanding ML requires knowledge of some mathematical concepts that build upon A-level standard mathematics, specifically: Linear Algebra and Continuous Optimisation. This will be taught in-place. Students will see motivating real world problems, the ML techniques required to solve them, the underlying mathematics needed for the technique and their practical implementation. Practicals will be taught using a python-based modern machine learning library such as TensorFlow or PyTorch and so students will gain experience with the declarative programming paradigm (building on the Software stream).

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 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