School of Computer Science BCS accreditation 2021 - 2026
[Home]
Computer Science MEng (Hons) - COMP24112 Machine Learning
Return to programme overview.
2.1.1 Knowledge and understanding of facts, concepts, principles & theories
This course has the following learning outcomes: (1) Describe essential and fundamental concepts in machine learning, including supervised and unsupervised learning, classification, regression and clustering, essential elements for building a machine learning system, and apply the knowledge to construct a machine learning task; (2) Explain different supervised learning models studied in the course unit, compare their differences, strengths and weaknesses, and apply the knowledge to decide which is appropriate for a particular application; (3) Explain clustering algorithms studied in the course unit and their applications; (4) Describe fundamental concepts in model evaluation and selection, explain the training, validation and testing processes, different methods for hyperparameter selection.
Assesement : Examination, Lab work
Assesement : Examination, Lab work
2.1.2 Use of such knowledge in modelling and design
This course has the following learning outcomes: Apply knowledge on a few machine learning models identified in the course unit to design learning systems, and analyse results as well as implication.
Assesement : Lab work
Assesement : Lab work
2.1.3 Problem solving strategies
This course has the following learning outcomes: Implement and apply a few machine learning models identified in the course unit to and solve real-world problems, and analyse results as well as implication.
Assesement : Lab work
Assesement : Lab work
2.1.4 Analyse if/how a system meets current and future requirements
This course has the following learning outcomes: Discuss the differences (including limitations and advantages) between parametric and non-parametric, between deterministic and probabilistic models, and interpret their results.
Assesement : Examination
Assesement : Examination
2.1.5 Deploy theory in design, implementation and evaluation of systems
This course has the following learning outcomes: (1) Recognise general factors that affect the performance of a machine learning system, and be able to use these to analyse and learn from data; (2) Apply the knowledge to use data, design machine learning experiments, and make observations from results. Also implementation of designed learning system is required.
Assesement : Lab work
Assesement : Lab work
2.1.6 Recognise legal, social, ethical & professional issues
This course has the following learning outcomes: Recognise and describe issues regarding ethics in machine learning.
Assesement : Individual coursework
Assesement : Individual coursework
2.1.7 Knowledge and understanding of commercial and economic issues
This course has the following learning outcome: Discuss the differences (including commercial and economic concerns) between models of different complexity levels, and interpret their results.
Assesement : Not Assessed
Assesement : Not Assessed
2.2.1 Specify, design or construct computer-based systems
This course requires learning outcome on design and implementation of machine learning systems, which are computer based.
Assesement : Lab work
Assesement : Lab work
2.2.2 Evaluate systems in terms of quality and trade-offs
This course requires learning outcome on discussing the differences (including limitations and advantages, quality and trade-offs) between different machine learning models.
Assesement : Examination
Assesement : Examination
2.2.4 Deploy tools effectively
The lab works requires the use of machine learning and mathematical tools.
Assesement : Lab work
Assesement : Lab work
2.3.2 Development of general transferable skills
This courses requires problem solving and numeracy skills, also communication skills required in marking session.
Assesement : Lab work
Assesement : Lab work
3.1.2 Methods, techniques and tools for information modelling, management and security
This course's main topic is machine learning, which contribute the major methods/tools in information modelling.
Assesement : Examination, Lab work
Assesement : Examination, Lab work
3.1.4 Knowledge and understanding of mathematical and/or statistical principles
This course requires applying mathematical and statistical principles in understanding and design of machine learning models.
Assesement : Examination, Lab work
Assesement : Examination, Lab work
4.1.1 Knowledge and understanding of scientific and engineering principles
This course is about knowledge and understanding of machine learning models, which belongs to scientific and engineering principles.
Assesement : Examination, Lab work
Assesement : Examination, Lab work
4.1.2 Knowledge and understanding of mathematical principles
This courses requires understanding of the mathematical principles that support the design and derivation of machine learning algorithms.
Assesement : Examination
Assesement : Examination
4.1.3 Knowledge and understanding of computational modelling
This course's focus in machine learning models, which is a main group of computational modelling techniques.
Assesement : Examination, Lab work
Assesement : Examination, Lab work