Module Specification

Deep Learning

Module Specification

Deep Learning : Crafting Tomorrow's Intelligent Systems Today


Data is the new language of innovation, deeply intertwined with decision science and modern technology. As data grows in complexity, so does the challenge of harnessing its full potential. Transcending traditional confines, this module offers a sophisticated toolkit to unlock data possibilities, catering to those keen on transforming insights into groundbreaking applications.

Throughout this module, you will comprehensively understand and manipulate state-of-the-art neural networks. Cover the essentials from artificial neurons and feedforward networks to advanced techniques like batch normalisation and dropout. Expand your knowledge with Convolutional Neural Networks for image tasks and dive into the workings of Recurrent Neural Networks for sequential data. The course navigates the terrain of NLP with transformers, explores representation learning with autoencoders, and challenges common misconceptions with Generative Adversarial Networks.

Arm yourself with practical skills and insightful strategies for developing cutting-edge deep learning models. This module prepares you to face diverse data problems, transforming complexity into clarity. Sharpened by direct experience and enhanced by critical optimisation strategies, become proficient in designing and refining neural networks that push technological boundaries. Join an expert-led exploration that empowers and inspires.


Mode(s) of Study Code CATS Credits ECTS Credits Framework HECoS code
Full-time Blended Learning
Part-time Blended Learning		 DL71 30 15 FHEQ - L7

Prerequisites and Co-requisites

  • Prerequisite: Applied Machine Learning

Learning Outcomes

Code Attributes developed Outcomes
LO1 Knowledge and Understanding Demonstrate comprehensive understanding of deep learning architecture components such as neural networks, CNNs, RNNs, and transformers.
LO2 Intellectual Skills Critically analyse performance metrics of various deep learning models to evaluate their effectiveness in different tasks.
LO3 Intellectual Skills Develop critical solutions to address training challenges like overfitting, using techniques such as dropout and batch normalisation.
LO4 Technical/Practical Skills Design and implement neural networks using deep learning frameworks to solve complex data problems.
LO5 Technical/Practical Skills Utilise and optimise autoencoders and GANs for data representation, anomaly detection, and image synthesis.
LO6 Professional/Transferable Skills Apply ethical considerations in the deployment of neural networks, ensuring responsible use in professional practice.

Content Structure

Week Topic
Week 1 Introductory lecture
Introduces the module, outlining its relevance to the field and connections to other topics. It provides an overview of the content structure, key references, and assessment details.
Week 2 Neural Network Fundamentals
Build a solid foundation in neural networks to understand why they are the backbone of deep learning. Explore the fundamental concepts of artificial neurons and how they mimic biological neurons. Delve into feedforward networks to see how inputs transform through layers to produce outputs. Learn the importance of the backpropagation algorithm in training networks by minimising error. By grasping these basics, you'll appreciate why neural networks are essential for modelling complex patterns in data.
Week 3 Training Deep Networks
Discover why training deep feedforward networks poses unique challenges. Learn how activation functions like ReLU and Sigmoid influence the learning process and model performance. Understand issues like vanishing and exploding gradients that hinder deep network training. Explore techniques like batch normalisation and dropout to stabilise learning, prevent overfitting, and optimise models. By mastering these methods, you'll overcome the hurdles of training deep networks effectively.
Week 4 Convolutional Neural Networks
Dive into convolutional neural networks to understand why they are transformative for image processing tasks. Learn how convolutional layers detect local patterns and hierarchies in data. Examine architectures like LeNet, VGG, and ResNet to appreciate their innovations and improvements in image classification tasks. By exploring CNNs, you'll see why they are indispensable for applications involving visual data.
Week 5 Recurrent Neural Networks
Understand why recurrent neural networks are essential for modelling sequential data like text or time-series. Explore how they capture temporal dependencies through feedback connections. Learn about LSTM and GRU units that address the vanishing gradient problem, enabling networks to learn long-term dependencies. By studying RNNs, you'll grasp their importance in tasks where order and context are crucial.
Week 6 Attention Mechanisms & Transformers
Discover why attention mechanisms have revolutionised natural language processing and other fields. Learn how self-attention allows models to focus on relevant parts of the input when generating outputs. Explore transformer architectures like BERT and GPT that leverage attention for parallel processing, leading to significant performance gains. By understanding attention, you'll appreciate how models capture complex relationships in data.
Week 7 Autoencoders & Representation Learning
Learn why autoencoders are powerful tools for unsupervised representation learning. Understand how they compress data into lower-dimensional codes and reconstruct inputs. Explore variational autoencoders that introduce probabilistic elements for generating new data samples. See how autoencoders are used in anomaly detection and latent space exploration, enabling models to capture underlying data structures.
Week 8 Generative Models & GANs
Investigate why generative adversarial networks are exciting developments in data generation. Understand the adversarial training process where a generator and discriminator compete, leading to realistic outputs. Explore models like DCGAN and CycleGAN that extend GANs to specific applications like image synthesis and style transfer. By studying GANs, you'll grasp the challenges and solutions in training generative models.
Week 9 Optimisation Techniques in Deep Learning
Grasp why optimisation is crucial for effective neural network training. Learn how optimisers like Adam and RMSProp adapt learning rates during training for better convergence. Understand learning rate scheduling to fine-tune training progress. Explore regularisation methods like weight decay to prevent overfitting. By mastering optimisation techniques, you'll enhance model performance and ensure reliable results.
Week 10 Hyperparameter Tuning & Model Evaluation
Realise the importance of hyperparameter tuning in achieving optimal deep learning models. Learn systematic approaches like grid search and random search to adjust parameters. Understand how to evaluate models using appropriate metrics and validation techniques. Appreciate why rigorous testing and evaluation are essential to validate model effectiveness and generalise to new data.

References/Indicative Reading List

Importance ISBN Description
Core Textbook 9781800206137 Saitoh, Koki. Deep Learning from the Basics: Python and Deep Learning: Theory and Implementation. Packt Publishing, 2021
Core Textbook 9781838640859 Rivas, Pablo. Deep Learning for Beginners: A beginner's guide to getting up and running with deep learning from scratch using Python. Packt Publishing, 2020
Core Textbook 9781977610720 Slavio, John. Deep Learning and Artificial Intelligence: A Beginners’ Guide to Neural Networks and Deep Learning. CreateSpace Independent Publishing Platform, 2017
Supplementary Reading 9780262537551 Kelleher, John D. Deep learning. MIT press, 2019
Supplementary Reading 9781492082187 Buduma, Nithin, Nikhil Buduma, and Joe Papa. Fundamentals of deep learning. O'Reilly Media, Inc, 2022
Supplementary Reading 9781491914250 Patterson, Josh, and Adam Gibson. Deep learning: A practitioner's approach. O'Reilly Media, Inc., 2017
Supplementary Reading 9781838646301 Ranjan, Sumit and Senthamilarasu, S. Applied Deep Learning and Computer Vision for Self-Driving Cars: Build autonomous vehicles using deep neural networks and behavior-cloning techniques. Packt Publishing, 2020
Supplementary Reading 9780262035613 Goodfellow, Ian, Bengio, Yoshua and Courville, Aaron. Deep Leaning. MIT Press, 2016

The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning. The first part of the book covers some key concepts of ML. The second part explains man Deep Learning models that are well defined and are frequently used.
The third part of the book is mostly devoted to more scientific aspects of DL and topics that are being studied at large by research.
Supplementary Reading 9781617296864 Chollet, François . Deep Learning with Python, Second Edition. Manning, 2021

This book is written by the creator of the Keras library. It provides very detailed examples of difference deep learning networks that are implemented using Keras and TensorFlow. The book is accompanied with a Github repot to access to code thorugh Jupyter notebooks. Also, this makes readers familiar with the structure that is used in Keras.io, a handy website with many exmaples to get involved with most recognized deep learning algorithms.

Student Workload

The methods of teaching and learning for this module are based on the School's Technical 30 teaching system, consisting of the following activities.

Activity Total hours
Introductory lecture

This is the first weekly session, dedicated to providing a comprehensive introduction to the module. The module leader will present an overview of the subject, elucidating its importance within various digital engineering professions and its interrelation with other modules. Students will need no preparation ahead of attending this session.

The module leader will provide a structured breakdown of the content to be covered in the subsequent 9 sessions. Students will also receive an outline of the essential reference materials, alongside suggestions for supplementary reading. The format and criteria for the summative assessment will be delineated, followed by a dedicated period for questions and answers.

A recording of the session will be available to facilitate async engagement for any other student who missed the class, also offering an opportunity to review the content again.

 1.50
Concept learning (knowledge graph)

Our institution's approach to teaching is primarily based on flipped learning. Ahead of each weekly session (Workshop/Lab), students will be required to study the essential concepts that are used in the coming session so they are familiar with the theories and ideas related to that session. The study material will be in the form of written content, illustrations, pre-recorded lectures and tutorials, and other forms of content provided through the AGS.

This content is self-navigated by the students, accommodating different learning styles and schedules, allowing students to watch or listen to them at their own pace and review them as needed.

 36.00
AI formative assessment

Once each concept of the theory is studied, students will be prompted to engage in formative assessment with instant AI feedback. They include multiple-choice questions, socratic questions and answers, written questions, role-play and other AI-assisted practice scenarios.

The purpose of this automated formative assessment is to provide students with immediate feedback on their understanding of module material and highlight any areas that need support or further study. They are also used to track student progress, boost motivation and promote accountability.

 18.00
Workshop/Lab Sessions

Those studying in the blended learning mode will attend these 9 weekly classes (in person or remotely) during weeks 2 to 10. These sessions will complement the theory already studied during the preceding week (in our flipped-learning model), with discussions, analysis, practice or experience . They will be interactive and participatory, rather than one-way lectures. There will also be an opportunity for Q&A in every session. Depending on the nature of the content, challenges and learning activities will be pre-designed to apply flipped learning. They may include hands-on project work, group discussions or debates, roleplay, simulation, case studies, presentations, and other learning activities and opportunities. These workshops present an opportunity to apply critical thinking and problem-solving skills. They also encourage collaboration and foster a sense of community among students.

 27.00
Independent reading, exploration and practice

This activity challenges students to engage with the reference material and independently explore and analyse academic literature related to the course topic. Students are expected to select relevant sources, practice critical reading skills, and where applicable technical skills, and synthesise information from multiple references. This is an opportunity to enhance research abilities, critical thinking, and self-directed learning skills while broadening and deepening subject knowledge.

 153.50
Summative assessment

Summative assessments are used to evaluate student learning at the end of a module. These assessments can take many forms, including exams, papers, or presentations. Instructors can use summative assessments to measure whether students have achieved the learning outcomes for the module and provide them with a sense of their overall progress. Summative assessments can also be used to evaluate the effectiveness of the teaching methods used in the module.

 64.00
300.00

Assessment Patterns

Weighting Format Outcomes assessed
60% Technical Analysis and Solution Assessment
This assessment requires students to develop a solution to a complex problem within a simulated domain, followed by a detailed analysis and reflection on their design and its theoretical underpinnings. The aim is to assess students' abilities to design practical solutions, critically analyse their work, and articulate their understanding of the technical and theoretical aspects of the module.		 K LO1
I LO2
I LO3
T LO4
T LO5
P LO6
40% Invigilated Exam
This is a time-limited and closed-book exam with a mix of multiple-choice and analytical written questions that students undertake during the summative assessment period as scheduled under the School’s remote invigilation conditions to ensure quality and academic integrity.

The exam enables the students to demonstrate their successful attainment of the module learning outcomes, primarily related to knowledge and understanding, and secondarily related to Professional/Transferable Skills.

The analytical written questions will consist of problem questions representing issues and dilemmas students are likely to encounter in professional life and students have to synthesise and apply what they have learnt on the module in order to produce sound and reasoned judgements with respect to the problem.

To enable the students to practice and prepare, various formative assessment activies, including quizzes and a AI-augmented assignments and mock exams are built into the module. Additionally, throughout the course, students will regularly receive feedback on their knowledge and assignments from AI as well as peers and staff to indicate how to improve future work and how to give constructive feedback to others.		 K LO1
I LO2
I LO3
P LO6

Programmes this module appears on

Programme Term Type
1 MSc AI and Machine Learning 2 Optional
Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change.
Module Spec: Deep Learning : Crafting Tomorrow's Intelligent Systems Today (DL71)