Module manager: Dr Nabi Omidvar
Email: M.N.omidvar@leeds.ac.uk
Taught: 1 Jan to 28 Feb, 1 Jan to 28 Feb (adv year), 1 Jul to 31 Aug View Timetable
Year running 2026/27
This module is not approved as an Elective
This module introduces the principles and practice of artificial neural networks and deep learning as a foundation for modern artificial intelligence (AI). It explores how layered representations enable machines to learn from complex data, including images, sequential data such as text and time series, and relational data such as graphs. Students learn both the underlying concepts and the practical skills needed to design, train, and evaluate deep learning models across these different data modalities and their combinations.
This module aims to develop both conceptual understanding and practical competence in the design and implementation of deep learning models. It explores how artificial neural networks, as universal function approximators, can learn hierarchical representations of data and how core ideas in representation learning extend across modalities to underpin advanced applications in computer vision, natural language processing, and generative AI. A key focus is on understanding the relationship between data, model architecture, and the assumptions that guide learning, showing how design choices influence what a model captures, how it generalises, and the inductive biases that shape its performance. Learning activities combine explanatory material, visual illustrations, guided examples, and hands-on exercises that progressively build intuition and technical fluency, enabling students to design, train, and critically analyse deep models across diverse data types.
On successful completion of the module students will have demonstrated the following learning outcomes relevant to the subject:
1. Explain the principles of artificial neural networks and how they approximate complex relationships through layered representations.
2. Apply deep learning architectures to model different data modalities, including images, sequences, and relational data.
3. Design and implement neural network models, selecting appropriate architectures and training procedures for specific tasks.
4. Assess how data characteristics, architectural choices, and inductive biases influence model behaviour, performance, and generalisation.
5. Experiment with training strategies that include building models from scratch and fine-tuning pre-trained foundation models.
On successful completion of the module students will have demonstrated the following skills learning outcomes:
1. Apply structured problem-solving and analytical reasoning to design, evaluate, and refine solutions for complex, data-driven tasks.
2. Demonstrate adaptability and self-directed learning by integrating new methods, tools, or frameworks to address evolving challenges.
3. Communicate technical concepts, model results, and insights effectively to diverse audiences using clear, accurate, and engaging formats.
4. Apply integrated problem-solving and systems thinking to design and refine deep learning models.
5. Exercise critical evaluation and reflective practice to assess approaches, interpret outcomes, and improve performance over time.
Indicative content for this module includes:
· Fundamentals of artificial neural networks and representation learning
· Feedforward architectures and training using gradient-based optimisation
· Convolutional neural networks for spatial data and visual recognition
· Recurrent and transformer-based models for sequential data such as text and time series
· Graph neural networks and relational learning for structured and networked data
· Autoencoders, variational autoencoders, and related approaches to generative and unsupervised representation learning
· Regularisation, normalisation, and optimisation strategies for stable and efficient training.
| Delivery type | Number | Length hours | Student hours |
|---|---|---|---|
| Discussion forum | 6 | 1 | 6 |
| WEBINAR | 6 | 1 | 6 |
| Independent online learning hours | 42 | ||
| Private study hours | 96 | ||
| Total Contact hours | 12 | ||
| Total hours (100hr per 10 credits) | 150 | ||
1. Webinar-Based Discussion and Q&A
2. Weekly Practical Exercises
| Assessment type | Notes | % of formal assessment |
|---|---|---|
| Online Assessment | ~20 questions about different scenarios | 20 |
| Coursework | Technical Report | 80 |
| Total percentage (Assessment Coursework) | 100 | |
This module will be reassessed through a 100% individual assessment in the same format as Assessment 2 (coursework project). The reassessment will involve a practical project that requires students to apply and integrate the knowledge and skills developed across all learning outcomes.
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