Syllabuses - PG

CS824 - Quantitative Methods for Artificial Intelligence

TIMETABLETEACHING MATERIAL
Credits10
Level5
SemesterSemester 1
Mode of Delivery
  • Online
  • Attendance
Availability

Mandatory

Prerequisites

None

Learning Activities Breakdown

Lectures: 12 hours (online) | Lab: 12 hours | Tutorial: 6 hours | Private Study: 70 hours

Items of Assessment2
Assessment
  1. Group-based lab submissions (30%): During three out of the six labs, which will involve material provided as Jupyter notebooks, students will work in groups to solve a set of tasks and prepare a common submission as a Jupyter notebook.
  2. Individual coursework assignment (70%): Students will individually critique two different Kaggle notebooks and reflect on the task(s) the authors are attempting to address. They will comment on the steps that require use or understanding of the quantitative methods reviewed in this module. They will submit two annotated Jupyter notebooks and a pdf report.
ILO Assessment Mapping
Education for Sustainable Development Competences
  • Problem Solving
  • Critical Thinking
Pedagogical Methods Used to Support Competency Development
Sustainable Development Goals
  • Quality education
  • Industry, innovation and infrastructure
  • Partnerships for the goal
Resit

Individual coursework assignment (100%): Students will individually critique three different Kaggle notebooks and reflect on the task(s) the authors are attempting to address. They will comment on the steps that require use or understanding of the quantitative methods reviewed in this module. They will submit three annotated Jupyter notebooks and a pdf report.

LecturerDidier Devaurs

Aims and Objectives

The aim of this class is to provide students with the foundations of mathematics that are required to understand modern Artificial Intelligence techniques. The class will focus on three main topic areas: linear algebra, probability and statistics.

Learning Outcomes

– understand the statistical techniques used in modern AI/Deep Learning: exploratory data analysis (EDA), statistical distributions, significance testing, 'classical' and Bayesian inference;
– understand how to apply probability theory to common problems in modern AI/Deep Learning: randomness, probability distributions, variance, expected values, etc;
– gain an appreciation of how techniques from linear algebra are used in modern AI/Deep Learning: vectors, matrices, tensors, etc.

Syllabus

1. Probabilities are used to make assumptions about the underlying data when designing deep learning or AI algorithms. As it is important to understand key probability distributions, this part of the course will cover: Elements of Probability, Random Variables, Distributions, Variance, Expectation, etc.
2. Statistical methods are used in AI to analyse data and quantify the performance of algorithms. This part of the course will cover: mean, standard deviation, confidence intervals, statistical methods for data analysis, use of statistics in performance measurement, and an introduction to statistics in Python.
3. Linear algebra notations are used in Machine Learning to describe the parameters and structure of algorithms. This makes linear algebra necessary to understand how neural networks are put together and how they operate. This part of the course will cover: Scalars, Vectors, Matrices, Tensors, Matrix Norms, Special Matrices, and Eigenvalues / Eigenvectors.

Recommended Reading

This list is indicative only – the class lecturer may recommend alternative reading material. Please do not purchase any of the reading material listed below until you have confirmed with the class lecturer that it will be used for this class.

Various items of reading material will be suggested on the MyPlace page of this module. 

Last updated: 2026-08-11 13:53:31