Module Specification

Deep Learning

London school of INNOVATION

Module Specification

Deep Learning : Unlock Cutting-Edge AI with Mastering Deep Learning


Deep Learning is a subset of machine learning, where the algorithms are based on neural networks consisting of three to many layers. Usually, such networks are very large and can have more than a billion parameters that need to be learned. This has been made possible with the advent of powerful parallel processing units, large training networks can be trained to handle complex tasks such as conversational AI and self-driving cars. The behaviour of a network, whether it is designed for facial recognition or machine translation, is dependent on how the layers are structured and interact with each other.

In this module, students will look at the history of deep learning. They will explore how to build deep neural networks and Multi-Layer Perceptron. Some of the most famous tools for creating deep learning networks will be considered, such as PyTorch, TensorFlow, and Keras, and Normalisation techniques at data and layer levels for model generalisation will be explained. The module will cover Convolutional Neural Networks, and also Transfer Learning and Recurrent Neural Networks, Neural Transformers, Generative Adversarial Networks (GANs), and consider Graph Convolutional Networks too. Explainable AI will be a part of the module, and also deep learning development on the cloud. The course will also provide information to get the participants ready for designing and training networks either from scratch or from existing trained models. A step-by-step walkthrough of the algorithms will be provided to enable the creation of generalized deep learning models. Generalization is the process of training a model so that it can handle samples outside of the set it was used for training.


Code Number of Credits ECTS Credits Framework HECoS code
DL71 30 15 FHEQ - L7

Learning outcomes

Code Attributes developed Outcomes
LO1 Knowledge and Understanding Systematic understanding of deep learning architectures and frameworks.
LO2 Intellectual Skills Critically analyse neural network structures and functionalities, including perceptrons and layered architectures.
LO3 Technical/Practical Skills Apply transfer learning techniques to adapt pre-trained models to new domains and tasks.
LO4 Technical/Practical Skills Construct deep neural networks using leading frameworks like PyTorch, TensorFlow, and Keras.
LO5 Technical/Practical Skills Implement convolutional and recurrent neural network models for image and sequential data processing.
LO6 Professional/Transferable Skills Exercise sound judgement and ethical responsibility in meeting client and other stakeholder needs.

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
T 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
P LO6

Student workload

Activity Total hours
Introductory lecture 1.50
Concept learning (knowledge graph) 36.00
AI formative assessment 18.00
Workshop/Lab Sessions 27.00
Independent reading, exploration and practice 153.50
Summative assessment 64.00
300.00

Prerequisites and Co-requisites

  • Prerequisite: Applied Machine Learning 1

Content Structure

Week Chapter Name Chapter Description
Week 1 Neural Networks Students investigate the storied past of neural networks, gaining an appreciation for the milestones that paved the way for today's deep learning achievements. The chapter also delves into real-world applications across diverse sectors, illustrating the breadth of deep learning's capabilities and its influence on industries like healthcare, finance, and more.
Week 2 Perceptrons Here, students immerse in the fundamental concepts of deep neural networks, focusing on the intricate workings of perceptrons. The chapter provides a conceptual framework for understanding the complexities of multi-layered networks and their vast parameter spaces as a prelude to practical model building.
Week 3 PyTorch, TensorFlow, and Keras The module transitions into an examination of the principal tools that drive deep learning innovation. Comparing frameworks such as PyTorch, TensorFlow, and Keras, students will understand the nuances and strengths of each, laying the groundwork for practical model development and deployment.
Week 4 Generalisation in Deep Learning With a lens on generalisation, this chapter addresses the training paradigms aimed at enhancing model performance on unseen data. Students will consider the landscape of normalisation techniques, hyperparameter tuning, and methods to counter gradient-related problems.
Week 5 Visual Perception Exploring the nuances of image data processing, this chapter familiarises students with the concept and architecture of Convolutional Neural Networks. It focuses on their role in feature extraction and the hierarchical structuring of convolution and pooling layers significant in visual recognition tasks.
Week 6 Transfer Learning and Neural Fine-Tuning Students engage with the strategic practices of transfer learning, highlighting its efficiency and effectiveness in adapting pre-trained models to novel tasks. The chapter emphasises the technical aspects of modifying network layers and adjusting learning rates, enabling fluency in customising deep neural architectures.
Week 7 Sequential Data and Temporal Patterns This chapter introduces Recurrent Neural Networks as a potent tool for processing time series data, vital for applications requiring memory of past information. Students will comprehend the principles that make RNNs apt for predictions in sequence data scenarios.
Week 8 Transformers The transformative impact of neural transformers on natural language processing is dissected, while also acknowledging their spread to other data forms. Students explore the encoder-decoder architecture, attention mechanisms, and unique abilities in handling sequential data without recurrence.
Week 9 Generative Adversarial Networks Delving into the creative aspect of deep learning, this chapter introduces the concept of generative models, specifically GANs and their variants. Students learn to navigate the synthesis of new, diverse data samples, grappling with issues such as mode collapse.
Week 10 AI and Cloud Infrastructure A dual focus on explainable AI principles and cloud-based development environments culminates the technical content of the module. This chapter promotes transparency in model decision-making processes and utilises cloud resources to scale deep learning operations.

Module References

Type Description
Video Deep Learning with Real-World Projects
Book 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.
Book 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.

Methods of teaching/learning


Introductory lecture (1.50 hours)

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.


Concept learning (knowledge graph) (36.00 hours)

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.


AI formative assessment (18.00 hours)

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.


Workshop/Lab Sessions (27.00 hours)

The 9 weekly sessions following the introduction (weeks 2 to 10) will be dedicated to teaching the contents of the module during interactive workshops. These sessions will complement the theory with practice, experience or analysis. Their purpose is to advance the student's cognition from 'knowledge' to 'understand' and 'apply'.

Depending on the nature of the content, challenges and learning activities will be pre-designed to apply flipped learning, and may include hands-on project work, group discussions or debates, roleplay, simulation, case study or other presentation, 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. There will be an opportunity also for Q&A in every session.


Independent reading, exploration and practice (153.50 hours)

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.


Summative assessment (64.00 hours)

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.

Programmes this module appears on

Programme Term Type
1 AI and Machine Learning (MSc) 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 : Unlock Cutting-Edge AI with Mastering Deep Learning (DL71)