The aim of the module is to provide students with a comprehensive understanding of deep generative models and their applications in various fields. Students will learn the probabilistic foundations and learning algorithms for generative models, including variational autoencoders, generative adversarial networks, diffusion models, and autoregressive models. It is suitable for students interested in AI and machine learning, particularly those interested in the field of generative AI. During this module, students will learn the skills and knowledge to build and train generative models for various applications.
A Master the concepts of probabilistic foundations and learning algorithms of deep generative models, including variational autoencoders, generative adversarial networks, diffusion models, and autoregressive models. B Develop comprehensive expertise in implementing and training deep generative models using appropriate deep learning frameworks. C Expertly evaluate and appraise the performance of generative models using appropriate metrics and visualisation techniques. D Collaborate systematically and creatively within teams in order to deal with complex generative AI issues that require communication and teamwork.
The teaching philosophy of the module follows very much the philosophy of Syntegrative Education. This has meant that the teaching delivery pattern, which follows more intensive block teaching, allows more meaningful contribution from industry partners. This philosophy is carried through also in terms of assessment, with reduction on the use of exams and increase in coursework, especially problem-based assessments that are project focused. The delivery pattern provides space in the semester for students to concentrate on completing the assessments. The module will be delivered through a combination of lectures, seminars, and labs. The lectures will provide essential information on the techniques of generative AI. Seminars will be designed to extend the material introduced in the lectures and will be based around exercise sheets. Students will complete the exercises and discuss them in workshops to further their understanding of the concepts covered in the lectures. In labs, students will use appropriate deep learning framework to implement generative algorithms and gain practical experience with the concepts covered in the lectures and tutorials. In addition, students will be expected to devote unsupervised time to private study. Private study will provide time for reflection and consideration of lecture material and background reading.