CS3ML: Machine Learning

Module code: CS3ML

Module provider: Computer Science; School of Mathematical, Physical and Computational Sciences

Credits: 20

ECTS credits: 10

Level: 6

When you’ll be taught: Semester 1

Module convenor: Dr Muhammad Shahzad, email: m.shahzad2@reading.ac.uk

Pre-requisite module(s): BEFORE TAKING THIS MODULE YOU MUST TAKE CS2DA AND TAKE CS2PP AND TAKE CS2AI (Compulsory)

Co-requisite module(s):

Pre-requisite or Co-requisite module(s):

Module(s) excluded:

Placement information: NA

Academic year: 2026/7

Available to visiting students: Yes

Talis reading list: Yes

Last updated: 25 March 2026

Overview

Module aims and purpose

The primary aim of this module is to equip students with a solid understanding of both foundational and advanced concepts in Machine Learning (ML), with a particular emphasis on Deep Learning (DL). The module introduces core learning principles before progressing to modern deep learning architectures and methodologies that underpin state-of-the-art AI systems. Specifically, the module covers a range of deep learning techniques, including Feedforward Neural Networks, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Attention-based models, and Transformer architectures, with applications in both natural language processing and computer vision. In addition, the module covers reinforcement learning and generative modelling approaches including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Diffusion Models, enabling students to understand data generation, representation learning, and modern generative AI techniques. The practical application of these methods is demonstrated through diverse real-world problems, such as classification, regression, predictive modelling, information extraction, language modelling, and signal processing (including vision and speech). Emphasis is placed on model training, validation, and evaluation, allowing students to gain hands-on experience in applying deep learning techniques to realistic datasets and problem settings.

Students will also be able to demonstrate their abilities in critical thinking to solve a large problem integrating components of data engineering, algorithm development and implementation; and professional and effective writing for algorithm development and software implementation.

Module learning outcomes

By the end of the module, it is expected that students will be able to:

1. Apply a variety of learning algorithms to a given data.
2. Evaluate various learning algorithms for optimal model selection.
3. Apply modern machine/deep learning tools/models to real-world problems to create a small-scale learning project.

Module content

The module covers the following topics:

• Core machine learning concepts (bias–variance trade-off, overfitting, regularization, ensembles)
• Optimization strategies (loss functions and gradient-based optimization methods)
• Deep neural network architectures, training strategies, hyperparameter tuning, and applications
• Generative modelling (e.g., VAEs, GANs, diffusion models) 
• Reinforcement learning (fundamental concepts and key algorithms)

Structure

Teaching and learning methods

The module consists of 2-hour lectures and 2-hour practical sessions per week. The lectures will introduce students the theories, concepts and underpinning principles specified in the indicative content while the supervised practical sessions will guide them to develop thorough understanding in implementing ML/DL algorithms for variety of different tasks. The formal lecture and practical sessions will enable students to apply the fundamental ML/DL techniques to solve a given problem, by demonstrating using programming, analysis and report writing. Moreover, these sessions will be supplemented with several forms of digital resources to support learning. The summative assessment consists of one piece of individually written coursework assignment which requires every student to demonstrate his/her achievement in developing a small-scale ML/DL solution.

Study hours

At least 44 hours of scheduled teaching and learning activities will be delivered in person, with the remaining hours for scheduled and self-scheduled teaching and learning activities delivered either in person or online. You will receive further details about how these hours will be delivered before the start of the module.

Please note the independent study hours above are notional numbers of hours; each student will approach studying in different ways. We would advise you to reflect on your learning and the number of hours you are allocating to these tasks.

Semester 1 The hours in this column may include hours during the Christmas holiday period.

Semester 2 The hours in this column may include hours during the Easter holiday period.

Summer The hours in this column will take place during the summer holidays and may be at the start and/or end of the module.

Assessment

Requirements for a pass

Students need to achieve an overall module mark of 40% to pass this module.

Summative assessment

Penalties for late submission of summative assessment

The Support Centres will apply the following penalties for work submitted late:

Assessments with numerical marks

• where the piece of work is submitted after the original deadline (or a DAS-agreed extension as a reasonable adjustment indicated in your Individual Learning Plan): 10% of the total marks available for that piece of work will be deducted from the mark for each calendar day (or part thereof) following the deadline up to a total of three calendar days;
• where the piece of work is submitted up to three calendar days after the original deadline (or a DAS-agreed extension as a reasonable adjustment indicated in you Individual Learning Plan), the mark awarded due to the imposition of the penalty shall not fall below the threshold pass mark, namely 40% in the case of modules at Levels 4-6 (i.e. undergraduate modules for Parts 1-3) and 50% in the case of Level 7 modules offered as part of an Integrated Masters or taught postgraduate degree programme;
• where the piece of work is awarded a mark below the threshold pass mark prior to any penalty being imposed, and is submitted up to three calendar days after the original deadline (or a DAS-agreed extension as a reasonable adjustment indicated in your Individual Learning Plan), no penalty shall be imposed;
• where the piece of work is submitted more than three calendar days after the original deadline (or a DAS-agreed extension as a reasonable adjustment indicated in your Individual Learning Plan): a mark of zero will be recorded.

Assessments marked Pass/Fail

• where the piece of work is submitted within three calendar days of the deadline (or a DAS-agreed extension as a reasonable adjustment indicated in your Individual Learning Plan): no penalty will be applied;
• where the piece of work is submitted more than three calendar days after the original deadline (or a DAS-agreed extension as a reasonable adjustment indicated in your Individual Learning Plan): a grade of Fail will be awarded.

Where a piece of work is submitted late after a deadline which has been revised owing to an extension granted through the Assessment Adjustments policy and process (self-certified or otherwise), it will be subject to the maximum penalty (i.e., considered to be more than three calendar days late). This will also apply when such an extension is used in conjunction with a DAS-agreed extension as a reasonable adjustment.

The University policy statement on penalties for late submission can be found at: https://www.reading.ac.uk/cqsd/-/media/project/functions/cqsd/documents/qap/penaltiesforlatesubmission.pdf

You are strongly advised to ensure that coursework is submitted by the relevant deadline. You should note that it is advisable to submit work in an unfinished state rather than to fail to submit any work.

Formative assessment

Formative assessment is any task or activity which creates feedback (or feedforward) for you about your learning, but which does not contribute towards your overall module mark.

Each topic in a week has defined learning tasks which will enable students to self-reflect on the learning.  

Outcomes of the formative assessment for each topic may be given in the guidance tutorial notes, online tests feedback.

Basic algorithms will be presented in pseudo codes and/or in executable codes (e.g., Python) towards weekly studies.

Reassessment

Additional costs