Deep Learning - 2025 entry

Deep Learning is a highly in-demand skill in AI. In this module you will study foundational and advanced deep learning techniques, understand how to build neural networks, and how to lead successful machine learning projects. You will learn key concepts, including for example, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and contemporary advancements such as Transformers, with practical applications across various domains. You will attend lectures providing in-depth coverage of theories and algorithms. In addition, you will attend lab sessions where you'll apply theoretical concepts to hands-on practices. This module is suitable for Computer Science, Mathematics and Engineering students and any students with experience in programming and foundational machine learning concepts.

Co-requisite modules: ECMM422 Machine Learning or ECMM445 Learning from Data

This module aims to provide you with a strong theoretical foundation and practical skills in deep learning. You will gain an in-depth understanding of fundamental and advanced neural network architectures and techniques, including for example, CNNs, RNNs, Transformers and attention mechanisms, Dropout, and BatchNorm. The module will also introduce you to state-of-the-art research topics and real-world applications in computer vision, natural language processing, and beyond. You will work on case studies from for example, autonomous driving, video understanding or healthcare. You will practice these ideas in Python and in popular deep learning frameworks such as TensorFlow or Pytorch. Through hands-on practice, you will develop the ability to design, train, and evaluate deep learning models, preparing you for both academic research and industry applications in AI.

On successful completion of this module you should be able to:

Module Specific Skills and Knowledge:

1. Accurately explain a range of key concepts and advanced models of deep learning.

2. Implement deep learning models to solve real-world problems.

Discipline Specific Skills and Knowledge:

3. Formulate relevant real-world challenges as problems suitable for deep learning approaches.

4. Critically evaluate the performance of different deep learning models and architectures and their application to a range of problems.

Personal and Key Transferable/ Employment Skills and Knowledge:

5. Effectively communicate insights and evaluations drawn from research papers.

6. Demonstrate independent study and research skills through conducting projects.

Reassessment will be by coursework in the failed or deferred element only. For referred candidates, the module mark will be capped at 50%. For deferred candidates, the module mark will be uncapped.

Basic reading:

• Goodfellow, I., Bengio, Y., Courville, A. and Bengio, Y., 2016. Deep learning (Vol. 1, No. 2). Cambridge: MIT press.

• Bishop, C.M. and Bishop, H., 2023. Deep learning: Foundations and concepts. Springer Nature.

• Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.

• Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł. and Polosukhin, I., 2017. Attention is all you need. Advances in neural information processing systems, 30.

Web-based and electronic resources: 

• ELE

Reading list for this module: