Intelligent Systems 3: Probabilistic & Deep Learning - COM00041H

«Back to module search

Module summary

This module looks at modern applications of neural networks and machine learning. The practical elements of the course will focus on implementing a range of systems to handle real-world problems and evaluating the results appropriately.

Related modules

Additional information

Students on the joint Computer Science and Mathematics courses who are interested in this module should first discuss the necessary prerequisite knowledge with the module leader.

Module will run

Occurrence	Teaching period
A	Autumn Term 2022-23

Module aims

This module follows on from Intelligent Systems 2, and looks at modern applications of neural networks and machine learning. The practical elements of the course will focus on implementing a range of systems to handle real-world problems and evaluating the results appropriately.

Module learning outcomes

• Understand 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

• Understand 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