Module manager: Professor Zhiqiang Zhang
Email: Z.Zhang3@leeds.ac.uk
Taught: Semesters 1 & 2 (Sep to Jun) View Timetable
Year running 2026/27
This module is not approved as a discovery module
This module builds on previous modules and provides students with knowledge and skills in more specialised topics in artificial intelligence. The module will provide students with an understanding of how to design, implement and evaluate advanced deep learning networks and their applications.
This module has the following objectives:
• To equip students with an understanding of deep learning methodology and to obtain hands-on experience in deep learning applications with modern development tools.
• To study advanced topics in different types of deep neural networks, such as, LSTM, convolutional networks, and autoencoders.
• To equip students with skills and knowledge in artificial intelligence essential for development of autonomous systems.
On successful completion of the module students will have demonstrated the following learning outcomes:
1. Apply knowledge of mathematics, statistics, natural science and engineering principles to the solution of complex artificial intelligence problems. Some of the knowledge will be at the forefront of artificial intelligence.
2. Analyse complex artificial intelligence problems to reach substantiated conclusions using first principles of mathematics, statistics, natural science and engineering principles.
3. Select and apply appropriate computational and analytical techniques to model complex artificial intelligence problems, recognising the limitations of the techniques employed.
4. Identify and analyse ethical concerns and make reasoned ethical choices informed by professional codes of conduct.
5. Adopt a holistic and proportionate approach to the mitigation of security risks.
Skills Outcomes
On successful completion of the module students will have demonstrated the following skills:
a) Application of science, mathematics and/or engineering principles
b) Problem analysis
c) Application of computational and analytical techniques
d) Professional ethics practice
e) Mitigate security risks
Topics may include, but are not limited to:
• Overview of deep neural network architectures and their training strategies.
• Training of modern deep neural networks
• Different types of deep neural networks, such as, LSTM, convolutional networks, and autoencoders.
• Development, validation and deployment of deep neural networks for multiple real-world applications.
• Real-world considerations of Artificial Intelligence applications.
| Delivery type | Number | Length hours | Student hours |
|---|---|---|---|
| Lecture | 5 | 2 | 10 |
| Practical | 14 | 2 | 28 |
| Independent online learning hours | 22 | ||
| Private study hours | 140 | ||
| Total Contact hours | 38 | ||
| Total hours (100hr per 10 credits) | 200 | ||
Students studying ELEC modules will receive formative feedback in a variety of ways, including the use of self-test quizzes on Minerva, practice questions/worked examples and (where appropriate) through verbal interaction with teaching staff and/or post-graduate demonstrators.
Check the module area in Minerva for your reading list
Last updated: 30/04/2026
Errors, omissions, failed links etc should be notified to the Catalogue Team