MS3S31 - Advanced Machine Learning 01 Sep 2021 - 31 Aug 2027 | Version 1

Associated Module Information

Module Code: MS3S31
Module Title: Advanced Machine Learning
Faculty: Faculty of Computing, Engineering and Science
Faculty Group: Computing and Mathematical Sciences
Faculty Sub Group: Mathematical Sciences
Module Leader: Moizzah Asif, Ian Fitzell
Module Team: Filippo Cavallari, Angelica Pachon, Rebecca Peters, Ieuan Griffiths
First Intended Intake: SEP 2021 Final Year of Intake: 2024
Date Closed:
Credit Value: 20 Credit Level: 6
Language: English
Percentage of Module Taught in Welsh: 0
Equivalent Module:
HECOS codes:
HECOS Code Weighting:

Document Version Information

Version 1
Valid From 01 Sep 2021
Valid To 31 Aug 2027

Module Aims

To provide students with an understanding of advanced machine learning algorithms.

To provide students with an understanding of machine learning software libraries for implementing advanced algorithms.

Content Summary

Linear Classifiers:

Linear Classifiers and Perceptron, hinge loss, margin boundaries and regularization, review of gradient descent and stochastic gradient descent.

Introduction to Neural Networks:

Feedforward neural networks, neurons, activation functions, back-propagation algorithm, train neural networks using stochastic gradient descent. Logistic regression as a Neural Network. Implementation using cutting-edge machine learning libraries.

Further topics in Neural Networks:

Convolutions, Convolutional Neural Networks, Regularization using Dropout, implementations and practical application for images classifications.

Sequential data, modelling sequential data using Recurrent Neural Networks, learning interactions, implementations and practical application for modelling real world data.

Unsupervised Learning:

Unsupervised learning paradigm, clustering, dimensionality reduction, anomaly detection.

Learning and Teaching Methods

Activity Type Hours
Lecture 10
Practical classes and workshops 10
Supervised time in studio/workshop 6
Work based learning 74
Directed Study 28
Formative Assessment - Independent 72
Total Hours Selected 200

Learning Outcomes

# Learning Outcome
LO1 Understand the advanced machine learning algorithms.
LO2 Select, implement and apply advanced machine learning algorithms in practical applications.

Module Requisites

N/A

Assessment Criteria

Assessment Category Assessment Type Description Duration Word Count Weight (%) Best of? Pass Mark
Portfolio Portfolio 1 Portfolio 0 6000 100 No 40

Assessment Matrix

Assessment Type Learning Outcomes
LO1 LO2
Portfolio 1 ✔ ✔

Reading List

Ben-David, S., & Shalev-Shwartz, S. (2014). Understanding Machine Learning. Cambridge University Press.

Courville, A., & Bengio, Y., & Goodfellow, I. (2017). Deep Learning. MIT Press.

Grus, J. (2019). Data Science from Scratch 2nd Edition. O’Reilly.

Mirjalili, V., & Raschka, S. (2019). Python Machine Learning. Springer.