FUNDAMENTALS OF MACHINE LEARNING FOR COMMUNICATIONS - 2025/6

Module Overview

This module offers a comprehensive introduction to Artificial Intelligence (AI) and Machine Learning (ML) with a focus on its applications in modern communication systems. By taking this module, the student builds a strong foundation of AI/ML starting from the mathematical basics (linear algebra, probability, optimization) and the main algorithms and models (e.g. Decision Trees, Support Vector Machines, Deep Neural Networks, etc.) to the modern generative models, and reinforcement learning. Through the coursework, the student will gain hands-on experience with key AI/ML models applied to modern communication systems. By the end of the module, the student will not only understand the theory of machine learning but also develop the practical skills needed to implement and evaluate models for real-world applications in communications.

Module provider

Computer Science and Electronic Eng

Module Leader

BOLOURSAZ MASHHADI Mahdi (CS & EE)

Number of Credits: 15

ECTS Credits: 7.5

Framework: FHEQ Level 7

Module cap (Maximum number of students): N/A

Module Availability

Semester 1

Prerequisites / Co-requisites

None

Module content

Indicative content includes the following:
¿ Introduction to AI/ML ¿ Key paradigms: supervised, unsupervised, and reinforcement learning; real-world applications in communications.
¿ Mathematical Foundations ¿ Linear algebra (vectors, matrices), probability and statistics (distributions, Bayes' theorem), and optimization techniques (gradient descent, stochastic gradient descent).
¿ Supervised Learning ¿ Regression models, decision trees, support vector machines (SVMs), multi-layer perceptrons and neural networks, and model evaluation techniques.
¿ Unsupervised Learning ¿ Clustering methods (k-Means, DBSCAN, hierarchical clustering), dimensionality reduction (PCA, autoencoders).
¿ Deep Learning Fundamentals ¿ Introduction to deep neural networks, convolutional neural networks (CNNs) for image processing, recurrent neural networks (RNNs),attention and transformers.
¿ Model Training and Optimization ¿ Loss functions, backpropagation, gradient descent variants, hyperparameter tuning, and regularization techniques.
¿ Generative Models ¿ Variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models.
¿ Reinforcement Learning ¿ Fundamentals of reinforcement learning, Markov decision processes (MDPs), Q-learning, and deep policy gradient methods.
¿ Application to Communication Systems ¿ Applications of various AI/ML techniques in future evolving communication systems and networks.

Assessment pattern

Alternative Assessment

N/A

Assessment Strategy

The assessment strategy is designed to provide students with the opportunity to demonstrate:
¿ Understanding of AI/ML concepts/principles, the corresponding mathematical/computational basics, as well as applications in modern and evolving communication systems.
¿ Ability to use the appropriate AI/ML paradigm to build efficient models for real-world problems and implement them effectively leveraging the relevant software tools, development environments, libraries, etc.
¿ Practical proficiency in using AI/ML tools, libraries, and development environments.

Thus, the summative assessment for this module consists of:
¿ Coursework on Network Security via Supervised Learning (addresses learning outcomes: 3, 4 and 5)
¿ Coursework on DNN-assisted Connection Establishment (addresses learning outcomes: 3, 4 and 5)
¿ Final Examination (addresses learning outcomes: 1 to 5)

The final examination is a closed-book invigilated examination. There are several questions each from different areas of the course. Some questions each may consist of a few sub-questions for testing knowledge, analytical, and design skills. The coursework assessments consist of using the Python programming language to perform a carefully designed experiment, with a report summarizing the outcomes. The purpose of the coursework is for students to practically apply the theoretical knowledge gained from the lectures to real-world applications in communication systems.

Formative assessment and Feedback:
The students will receive formative assessment / feedback in the following ways:
¿ During lectures, by informal Q&A sessions, feedback on tutorial examples discussed, etc.
¿ Feedback on tutorial problem sheets with sample questions and answers provided to prepare students for the final examination.

Module aims

• The aim of this module is to offer a fundamental course on the principles of modern AI/ML in the context of the future evolving wireless communication systems/networks. In particular the module focuses on basic learning paradigms and representative learning algorithms that have been widely exploited and explored across various communication domains in the past years.

Learning outcomes

Methods of Teaching / Learning

The learning and teaching strategy is designed to achieve the following aims:
¿ To introduce the basic ideas of AI/ML along with the necessary mathematical knowledge to set up a solid understanding for the fundamental learning algorithms.
¿ To learn to analyse real-world problems from a mathematical perspective and identify the appropriate AI/ML paradigm that can be used to build possible solutions.
¿ To learn basic programming skills and understanding of software tools, development environments, libraries and reusable components such as Python libraries.
¿ To learn skills of applying AI/ML methods to various use cases arising in future evolving communication systems leveraging the corresponding domain knowledge, and implementing the corresponding solutions with the appropriate computer software.

Learning and teaching methods include the following:
¿ Lectures and presentation of new material to students with associated in class discussions.
¿ Two Python based coding courseworks with associated written reports.
¿ Tutorial revision class to solve sample exam questions to prepare students for the final examination.

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

https://readinglists.surrey.ac.uk
Upon accessing the reading list, please search for the module using the module code: EEEM085

Other information

The Intelligent Communication Systems and Networks MSc program is committed to developing graduates with strengths in Employability, Digital Capabilities, Global and Cultural Capabilities, Sustainability, and Resourcefulness and Resilience. This module is designed to allow students to develop knowledge, skills, and capabilities in the following areas: Digital capabilities: By introducing students to the computing hardware and software needed to complete the coursework; by enriching the students programming skills for the AI/ML disciplines and the various deep learning libraries. Employability: By teaching students practical AI/ML skills which is the most welcomed skill set in the modern industry, e.g. exploring a component that addresses specific industrial problems. Global and cultural capabilities: By introducing ethics-related topics around AI/ML; by teaching machine learning techniques around data bias and domain adaptation, which is cornerstone to deploying AI/ML solutions across multiple cultures and in global scale.

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2025/6 academic year.