MACHINE LEARNING FOUNDATIONS - 2026/7

Module Overview

This module introduces students to the foundations of modern machine learning and AI. It is designed to be accessible to students from any disciplinary background, with no prior mathematics, programming, or technical preparation assumed. The pedagogical approach is informed by accessible, intuition-first learning resources that demonstrate AI fundamentals can be taught to non-specialist learners without requiring formal mathematical preparation or coding background. By the end of the module, students have a working conceptual grasp of how machine learning and modern AI systems behave - sufficient to engage critically with applied AI topics across a range of domains.

Module provider

Computer Science and Electronic Eng

Module Leader

SONG Yi-Zhe (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

The module follows an accessible, intuition-first curriculum covering the foundations of modern AI. Indicative themes include: what AI and machine learning are and how they learn from data; the major families of machine learning approaches; an introduction to neural networks; large language models and their capabilities and limits; AI for vision and other modalities; how AI is evaluated, where it works well, and where it fails. The pedagogical approach is explicitly designed to make these concepts accessible without formal mathematics or programming background. Specific topic mix and level of technical depth to be developed by the module lead in consultation with the programme team ahead of first delivery.

Assessment pattern

Alternative Assessment

None

Assessment Strategy

The assessment strategy is designed to provide students with the opportunity to demonstrate subject-specific knowledge and how this knowledge can be applied in the design of AI solutions to real world problems.
Thus, the summative assessment for this module consists of:

• Applied AI coursework (address learning outcomes 1-5)

• Invigilated Examination (address learning outcomes 1-4)

The coursework assignment is designed to allow students to demonstrate their strength and capabilities in demonstration of the application of knowledge to a proposed solution with a variety of different resources, with emphasis on reasoning about AI behaviour and articulating methodological choices in plain language. The invigilated exam format is designed to allow students to demonstrate their independent strength and capabilities in demonstrating embedded knowledge, application of knowledge and critical comment on proposed solutions across the breadth of contemporary AI paradigms.

Formative assessment and feedback:
This is provided via feedback gained from the problem classes which take place during scheduled lecture sessions, which can be used to prepare for the summative assessment.

Module aims

• Build intuitive understanding of how machine learning systems learn from data, without requiring formal mathematical preparation.
• Establish working familiarity with the breadth of modern AI: machine learning, neural networks, large language models, computer vision, and other contemporary methods.
• Develop students' ability to recognise where AI methods are appropriate, and where they fail, across professional contexts.
• Equip students with the conceptual fluency needed to engage productively with applied AI in their field.

Learning outcomes

Methods of Teaching / Learning

Lectures introduce concepts using visual, intuitive, and worked-example approaches. Tutorials revisit common conceptual stumbling blocks. Laboratory sessions provide hands-on experience with current AI tools - students see AI systems behave, fail, and recover, building intuition rather than mathematical fluency. Captured content and guided learning support asynchronous revision. Independent study consolidates understanding. The module's pedagogical philosophy follows accessible AI learning resources that deliberately avoid formal mathematics and coding - students learn what AI is doing, not how to derive it from first principles.

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: COMM081

Other information

At programme level the five pillars are developed cumulatively rather than in any single module: the Semester 1 core modules establish the foundations, the AI+X electives apply and deepen them within a chosen domain, and the dissertation consolidates them through independent work. As a core foundation module taken by every student at the outset, Machine Learning Foundations seeds this progression ¿ building the baseline digital fluency and self-efficacy that later modules assume and extend. It contributes most strongly in the following areas:
Digital Capabilities:
Laboratory sessions give students direct, hands-on experience of how modern AI systems behave, fail and recover, building genuine fluency with contemporary AI tools rather than mathematical abstraction. Students leave able to reason critically about the AI systems they encounter in any digital workplace.
Resourcefulness and Resilience:
Students enter with no prior AI background and, through scaffolded tutorials that revisit common conceptual stumbling blocks, build the confidence and self-efficacy to reason independently about an unfamiliar technical field ¿ the module's success is measured by what they can reason about, not what they can prove.

Programmes this module appears in

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 2026/7 academic year.