Explore UCD

UCD Home >

ACM41020

Academic Year 2024/2025

Maths of Machine Learning (ACM41020)

Subject:
Applied & Computational Maths
College:
Science
School:
Mathematics & Statistics
Level:
4 (Masters)
Credits:
5
Module Coordinator:
Assoc Professor Barry Wardell
Trimester:
Autumn
Mode of Delivery:
On Campus
Internship Module:
No
How will I be graded?
Letter grades

Curricular information is subject to change.

The aim of this course is to introduce Machine Learning from the point of view of modern optimisation and approximation theory.

About this Module

Learning Outcomes:

By the end of the module the student should be able to:
- Describe the problem of machine learning from the point of view of function approximation, optimisation, linear algebra, and statistics.
- Identify the most suitable approach for a given machine learning problem.
- Analyse the performance of various machine learning algorithms from the point of view of computational complexity and statistical accuracy.
- Implement a simple neural network architecture and apply it to a pattern recognition task.

Indicative Module Content:

Material will cover the following mathematical topics relevant to Machine Learning:

Highlights from Linear Algebra
- Matrix multiplication
- The four fundamental subspaces
- Types of Matrix
- Matrix factorisation
- Eigenvalues and eigenvectors
- Symmetric, positive definite matrices
- Singular values and singular value decomposition
- Vector and matrix norms

Understanding data
- Linear regression
- Principal component analysis

Support vector machines
- Introduction to support vector machines
- Optimisation
- Lagrange multipliers
- Limitations
- Soft margins
- Kernel trick
- Multiple classes

Neural networks
- Introduction to neural networks
- Activation functions
- Architecture of a neural network
- Training a neural network
- Calculus on computational graphs
- Efficient matrix multiplication
- Backpropagation
- Universal approximation theorem
- Cross-entropy cost function

Optimisation
- Introduction to optimisation
- Gradient descent
- Newton's method
- Momentum
- Stochastic gradient descent
- Adaptive methods

Student Effort Hours:
Student Effort Type Hours
Lectures

36

Specified Learning Activities

36

Autonomous Student Learning

36

Total

108


Approaches to Teaching and Learning:
Lectures, Problem Classes, Assignments

Requirements, Exclusions and Recommendations

Not applicable to this module.


Module Requisites and Incompatibles
Not applicable to this module.
 

Assessment Strategy
Description Timing Component Scale Must Pass Component % of Final Grade In Module Component Repeat Offered
Exam (In-person): 2 hour End of Trimester Exam End of trimester
Duration:
2 hr(s)
Standard conversion grade scale 40% No
40
No
Quizzes/Short Exercises: Weekly short quizzes Week 2, Week 3, Week 4, Week 5, Week 6, Week 7, Week 8, Week 9, Week 10, Week 11 Standard conversion grade scale 40% No
5
No
Assignment(Including Essay): Assignments Week 4, Week 7, Week 8, Week 10 Standard conversion grade scale 40% No
25
No
Practical Skills Assessment: Computer-based coding exam Week 12 Standard conversion grade scale 40% No
30
No

Carry forward of passed components
No
 

Resit In Terminal Exam
Spring Yes - 2 Hour
Please see Student Jargon Buster for more information about remediation types and timing. 

Feedback Strategy/Strategies

• Group/class feedback, post-assessment
• Online automated feedback

How will my Feedback be Delivered?

Not yet recorded.

Timetabling information is displayed only for guidance purposes, relates to the current Academic Year only and is subject to change.
Autumn Lecture Offering 1 Week(s) - Autumn: All Weeks Fri 10:00 - 10:50
Autumn Lecture Offering 1 Week(s) - Autumn: All Weeks Fri 16:00 - 17:50