Accessibility statement

Intelligent Systems 3: Probabilistic and Deep Learning - COM00172M

« Back to module search

  • Department: Computer Science
  • Module co-ordinator: Dr. Dimitar Kazakov
  • Credit value: 20 credits
  • Credit level: M
  • Academic year of delivery: 2021-22

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

Co-requisite modules

  • None

Prohibited combinations

  • None

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 cycle
A Autumn Term 2021-22

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

  • Apply the probabilistic basis of machine learning to problems

  • 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

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

  • Work on systems that handle larger amounts of training data and be able to discuss the problems and solutions

Assessment

Task Length % of module mark
Essay/coursework
Intelligent Systems 3
N/A 100

Special assessment rules

None

Reassessment

Task Length % of module mark
Essay/coursework
Intelligent Systems 3
N/A 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



The information on this page is indicative of the module that is currently on offer. The University is constantly exploring ways to enhance and improve its degree programmes and therefore reserves the right to make variations to the content and method of delivery of modules, and to discontinue modules, if such action is reasonably considered to be necessary by the University. Where appropriate, the University will notify and consult with affected students in advance about any changes that are required in line with the University's policy on the Approval of Modifications to Existing Taught Programmes of Study.