Module:

Latest Module Specifications

Current Academic Year 2025 - 2026

Our systems are undergoing maintenance and are temporarily unavailable. Please try again later.

Module Title
Module Code	(ITS: EE358)
Faculty		School
NFQ level		Credit Rating

Description

The principal purpose of the module is to provide students with knowledge in areas of mathematics that are required for Machine Learning. The knowledge is also required for many other engineering applications such as advanced circuit theory, quantum electronics and communication systems.

Learning Outcomes

1. 1E6C8FAA-BFD5-0001-CFFD-BD0074801A70
2. Perform vector and matrix operations and apply to problems of data representation and transformation.
3.
4.
5. 1
6. 1E6C8FAA-45BB-0001-6B67-1A001810110D
7. Apply the basic principles of probability theory, including the concepts of random variables, probability distributions, and conditional probability to model and analyze uncertainty in data.
8.
9.
10. 2
11. 1E6C8FAA-6765-0001-E8E0-188B18EB1343
12. Apply linear and non-linear regression techniques to model relationships between variables in data, evaluate model performance using appropriate metrics, and use these models to make predictions
13.
14.
15. 3
16. 1E6C8FAA-C86D-0001-D862-5960165B11FF
17. Identify appropriate statistical analysis techniques and apply them to assess the quality of data models.
18.
19.
20. 4
21. 1E6CD8BD-2531-0001-FE64-4C4919501C43
22. Compute gradients, partial derivatives, and directional derivatives and apply multivariate calculus to optimization problems.
23.
24.
25. 5

*Type*	*Hours*	*Description*
Workload	Full time hours per semester
Lecture	125	total time for lectures, class tests, tutorials and independent learning
Total Workload: 125

Type	Description	% of total	Assessment Date
Assessment Breakdown
In Class Test	Four in class quizzes on course material	25%	As required
Formal Examination	n/a	75%	End-of-Semester

Reassessment Requirement Type
Resit arrangements are explained by the following categories; RC1: A resit is available for both^* components of the module. RC2: No resit is available for a 100% coursework module. RC3: No resit is available for the coursework component where there is a coursework and summative examination element. ^* ‘Both’ is used in the context of the module having a coursework/summative examination split; where the module is 100% coursework, there will also be a resit of the assessment

Pre-requisite	None
Co-requisite	None
Compatibles	None
Incompatibles	None

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Introduction
What is machine learning? Mathematical underpinnings of machine learning.

Review of Linear Algebra
Vectors, matrices, inner and outer products, eigenvalues and eigenvectors, matrix inversion

Probability
Basic definition, probability density function, cumulative distribution function, common distributions, Normal distribution, Bayes’ Theorem, random variables, expectation, variance, moments, operations on random variables

Statistics
Parameter estimation, confidence intervals, hypothesis testing.

Review of Multivariate Calculus
Multivariate chain rule, Taylor series, gradients, partial derivatives.

Regression
Linear, non-linear and normal regression. Performance evaluation of regression models.

Optimization
What is optimization? Gradient descent as an optimization technique.

Indicative Reading List

Books:

Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong, Cambridge University Press; 1st edition (April 23, 2020): 0, Mathematics for Machine Learning, 978-110845514

Articles:
None

Other Resources

None