# ACM30100 Maths of Machine Learning

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

Show/hide contentOpenClose All

Curricular information is subject to change

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
- Newton's method
- Momentum

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
Learning Recommendations:

It is recommended that students should be familiar with material in vecter integral and differential calculus

Module Requisites and Incompatibles
Not applicable to this module.

Assessment Strategy
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Multiple Choice Questionnaire (Short): Weekly short MCQs Throughout the Trimester n/a Standard conversion grade scale 40% No

5

Practical Examination: Computer-based coding exams Throughout the Trimester n/a Standard conversion grade scale 40% No

30

Examination: 2 hour End of Trimester Exam 2 hour End of Trimester Exam No Standard conversion grade scale 40% No

40

Continuous Assessment: Assignments Varies over the Trimester n/a Standard conversion grade scale 40% No

25

Carry forward of passed components
No

Resit In Terminal Exam
Autumn Yes - 2 Hour
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.

Spring

Lecture Offering 1 Week(s) - 20, 21, 22, 23, 25, 26, 30, 32 Thurs 13:00 - 14:50
Lecture Offering 1 Week(s) - 24 Thurs 13:00 - 14:50
Lecture Offering 1 Week(s) - 29 Thurs 13:00 - 14:50
Lecture Offering 1 Week(s) - 31 Thurs 13:00 - 14:50
Lecture Offering 1 Week(s) - 33 Thurs 13:00 - 14:50
Lecture Offering 1 Week(s) - 20, 21, 22, 23, 24, 25, 26, 29, 30, 31, 32, 33 Tues 09:00 - 09:50
Spring