CS4S771 - Machine Learning and Autonomous Systems 01 Sep 2021 - 01 Oct 2028 | Version 2

Associated Module Information

Module Code: CS4S771
Module Title: Machine Learning and Autonomous Systems
Faculty: Faculty of Computing, Engineering and Science
Faculty Group: Computing and Mathematical Sciences
Faculty Sub Group: Computer Science
Module Leader: Janusz Kulon
Module Team: Carl Jones
First Intended Intake: SEP 2019 Final Year of Intake:
Date Closed:
Credit Value: 20 Credit Level: 7
Language: English
Percentage of Module Taught in Welsh: 0
Equivalent Module:
HECOS codes: 100992 - machine learning
HECOS Code Weighting: 100

Document Version Information

Version 2
Valid From 01 Sep 2021
Valid To 01 Oct 2028

Module Aims

To provide a broad introduction to machine learning and autonomous systems, approaches to their design and development, areas of application, available tools and the implications to society.

Content Summary

Introduction to Machine learning, Autonomous Systems, Agents and Reinforcement Learning.

Data preparation, data exploration and dimensionality reduction.

Pattern recognition: classification, clustering and prediction.

Neural Networks: regression, supervised learning, unsupervised learning, semi-supervised learning.

Agents, Multi-agent systems, Reinforcement learning.

Ethical considerations, privacy, interpretability and implications to society.

Learning and Teaching Methods

Activity Type Hours
Lecture 24
Practical classes and workshops 24
Independent Study 80
Directed Study 72
Total Hours Selected 200

Learning Outcomes

# Learning Outcome
LO1 To design and implement an autonomous system utilising appropriate methods, tools and models.
LO2 To critically explain, compare and contrast machine learning techniques and their use in the support of the creation of autonomous systems.
LO3 To explain societal and ethical issues associated with autonomous systems.

Module Requisites

N/A

Assessment Criteria

Assessment Category Assessment Type Description Duration Word Count Weight (%) Best of? Pass Mark
Asynchronous Assessment Presentation (Asynchronous) 1 Apply practical knowledge of machine learning techniques to solve a constrained problem and report on findings in the style of an academic poster supported by an oral presentation. 0 2000 50 No 40
Asynchronous Assessment Practical Written Work 1 Apply practical knowledge of machine learning techniques to solve a constrained problem and report on findings in the style of an academic paper. 0 2000 50 No 40

Assessment Matrix

Assessment Type Learning Outcomes
LO1 LO2 LO3
Presentation (Asynchronous) 1
Practical Written Work 1

Reading List

Reinforcement Learning: An Introduction. Richard S. Sutton and Andrew G. Barto (2018) The MIT Press, 2nd Edition, ISBN-13: 978-0262039246

Multi-Agent Machine Learning: A Reinforcement Approach. H. M. Schwartz (2014), Wiley, ISBN-10: 9781118362082

Mastering Machine Learning Algorithms. Giuseppe Bonaccorso (2018), Packt Publishing, ISBN-13: 978-1788621113

Building Machine Learning Systems with Python. Luis Pedro Coelho, Willi Richert, Matthieu Brucher (2018), Packt Publishing; 3rd edition, ISBN-13: 978-1788623223