Accessibility statement

Advanced AI Techniques for Creative Practice - TFT00110M

« Back to module search

  • Department: Theatre, Film, Television and Interactive Media
  • Credit value: 20 credits
  • Credit level: M
  • Academic year of delivery: 2024-25
    • See module specification for other years: 2023-24

Module summary

This module focuses on practical applications of deep learning-based AI solutions. This involves learning to identify design requirements to prototype personalised solutions for creative applications, customise and extend successful architectures, adapting them for creative industries such as theatre, film, television, art, music, interactive storytelling and more.

This module explains the building blocks of convolutional architectures, and how these have been combined in successful architectures, enabling excellent results for very different problems, ranging from image recognition to style transfer. Generative networks and state of the art stable diffusion techniques will also be introduced.

Professional requirements

Basic familiarity with computing skills is assumed, but no formal qualifications in Computer Science, Programming, or any other specific technical skills are required. The first modules of the programme are used to bring all students to the same level.

Module will run

Occurrence Teaching period
A Semester 2 2024-25

Module aims

  • To introduce deep artificial networks components.

  • To introduce a variety of successful CNN add GAN architectures, as well as the way they can be applied to creative industries.

  • To encourage code reuse, by showing a number of examples of effective customisation of existing architectures.

  • To demonstrate how techniques such as data augmentation and transfer learning can be used in real world scenarios.

Module learning outcomes

  • Be able to identify requirements of deep learning-based creative applications, in order to design them.

  • Be able to identify and apply the building blocks of deep networks, both generative and for synthesis.

  • Be able to customise and extend existing artificial networks architectures to novel applications in creative practice.

  • Be able to identify training and testing data requirements for deep learning models.

  • Be able to apply techniques to effectively mitigate the lack of training data.

Indicative assessment

Task % of module mark
Essay/coursework 100

Special assessment rules

None

Indicative reassessment

Task % of module mark
Essay/coursework 100

Module feedback

You will receive written feedback/mark in line with standard University turnaround times.

Indicative reading

Anantrasirichai, N. and Bull, D., 2021. Artificial intelligence in the creative industries: a review. Artificial Intelligence Review, pp.1-68.

Glassner, A., 2021. Deep learning: a visual approach. No Starch Press.

The artist in the machine https://www.artistinthemachine.net/


The information on this page is indicative of the module that is currently on offer. The University constantly explores 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. In some instances it may be appropriate for the University to notify and consult with affected students about module changes in accordance with the University's policy on the Approval of Modifications to Existing Taught Programmes of Study.