Introduction to Machine Learning module (AC50001)
20
AC50001
Semester 2
About the Module
This module will introduce you to some of the main approaches used for data analysis and machine learning. Students will gain knowledge and understanding of different algorithms, and gain skills in applying them to analyse data, make predictions, and evaluate performance. You will learn about:
- Probabilistic models
- Bayesian inference
- Linear models for regression and classification
- Maximum likelihood and MAP
- Neural networks and deep learning
- Unsupervised learning
- Performance evaluation
- Application examples
Credit Rating
There are 20 SCQF points available on this module.
Module Timetable
The module topics are delivered in the following order. The exact timing from week to week may vary slightly but will be approximately as follows.
Semester 2
| Week | Subject |
|---|---|
| 1 | Probability calculus, Bayes' rule |
| 2 | Distributions, expectations |
| 3 | Gaussians, mixture models |
| 4 | Bayesian analysis, MCMC |
| 5 | Bayesian networks |
| 6 | Clustering |
| 7 | Classification and regression, linear models |
| 8 | Neural networks, backpropagation |
| 9 |
Performance evaluation |
| 10 | Deep learning |
Assessment and Coursework
Coursework counts for 30% of the final module mark.
The final degree exam counts for 70% of the final module mark.
Assignments
Marking criteria are provided on My Dundee for all assignments so that you know what we are looking for when we are marking your coursework. Please ensure that you refer to these when completing assignments.
| Title | Week Given | Week Due | Effort Expected (hours) | Value (%) |
|---|---|---|---|---|
| Probabilistic models and inference | S2:4 | S2:8 | 10 | 10 |
| Classification | S2:8 | S2:11 | 20 | 20 |
Resources
All course material is available on My Dundee. This includes copies of lecture materials, practical exercises and assignments. The reading list for this module can be accessed from My Dundee, and provides recommended materials for completing the module.