Advanced AI Techniques for Creative Practice - TFT00110M
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 2025-26 |
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/