CSC-20067 - Module Specification
School of Computing and Mathematics
Faculty of Natural Sciences
For academic year: 2022/23 Last Updated: 19 January 2023
CSC-20067 - Machine Learning
Coordinator: Vishwash Batra Tel: +44 1782 7 33114
School Office: 01782 733075
Programme/Approved Electives for 2022/23
Available as a Free Standing Elective
Co-requisites
None
Prerequisites
None
Barred Combinations
None
Description for 2022/23
Aims
To provide an introduction to the concepts of statistical data analysis and machine learning. The module provides in-depth training in the use of machine learning tool kits in Python to analyse real world data and to deliver valuable insight that can be used to provide business services.
Intended Learning Outcomes
explain the fundamental vocabulary and concepts in machine learning: 1
apply machine learning to data using packages such as Scikit-Learn: 1
develop a complete data science project workflow which demonstrates understanding of ethical design: 1
evaluate algorithmic decision-making for bias and explainability using performance metrics and fairness testing: 1
apply machine learning to data using packages such as Scikit-Learn: 1
develop a complete data science project workflow which demonstrates understanding of ethical design: 1
evaluate algorithmic decision-making for bias and explainability using performance metrics and fairness testing: 1
Study hours
20 hours of practical: 10 x 2 hour practical sessions
10 hours of online lectures
20 hours coursework preparation
100 hours independent learning
10 hours of online lectures
20 hours coursework preparation
100 hours independent learning
School Rules
None
Description of Module Assessment
Structured report outlining planning, implementation and evaluation of a data science project
A 3000 word report of a data science project where learners are asked to develop a machine learning model to analyse and evaluate a data set. As part of the project the learners should design a workflow and demonstrate understanding and application of ethical design concepts throughout, including exploratory analysis and testing for bias and explainability.