Run by School of Computer Science and Electronic Engineering

20.000 Credits or 10.000 ECTS Credits

Semester 2

Organiser: Prof Ludmila Kuncheva

To extend the student's knowledge of machine learning acquired through module ICE-3701 (Machine Learning). To introduce them to modern-day challenges and solutions. Challenges include imbalanced data, streaming data and concept drift. Solutions include Classifier ensembles and Deep Learning neural networks.

Indicative content includes:

• Review of the fundamentals of machine learning: supervised and unsupervised learning, classifier models, feature selection.
• Classifier ensembles.
• Imbalanced data, streaming data and concept drift: machine learning solutions.
• Introduction to Deep Learning neural networks and their applications.

good

Equivalent to the range 60%-69%. Is able to analyse a task or problem to decide which aspects of theory and knowledge to apply. Solutions are of a workable quality, demonstrating understanding of underlying principles. Major themes can be linked appropriately but may not be able to extend this to individual aspects. Outputs are readily understood, with an appropriate structure but may lack sophistication.

excellent

Equivalent to the range 70%+. Assemble critically evaluated, relevant areas of knowledge and theory to construct professional-level solutions to tasks and questions presented. Is able to cross-link themes and aspects to draw considered conclusions. Presents outputs in a cohesive, accurate, and efficient manner.

threshold

Equivalent to 50%. Uses key areas of theory or knowledge to meet the Learning Outcomes of the module. Is able to formulate an appropriate solution to accurately solve tasks and questions. Can identify individual aspects, but lacks an awareness of links between them and the wider contexts. Outputs can be understood, but lack structure and/or coherence.

1. Understand the challenges of modern data and the potential of machine learning to address them.

2. Demonstrate knowledge of advanced machine learning methods at an algorithmic level.

3. Compose thoughts and findings in a clear, scientific manner.

4. Apply (by hand) some of the learned methods to toy problems.

5. Program some of the learned methods to solve toy and real-world problems.

Type	Name	Description	Weight
CLASS TEST	Class Test	Solve all problems.	20.00
COURSEWORK	Lab report	Solve all problems. Python code will be required.	20.00
COURSEWORK	Final article	An article-type report on experiments with challenging datasets.	60.00

		Hours
Private study	The students will revise the material given in the lectures, prepare for the class test, prepare the lab report and write the final article.	152
Laboratory	2 hours of labs x 12 weeks.	24
Lecture	2 hours of lectures x 12 weeks	24

• Literacy - Proficiency in reading and writing through a variety of media
• Numeracy - Proficiency in using numbers at appropriate levels of accuracy
• Computer Literacy - Proficiency in using a varied range of computer software
• Self-Management - Able to work unsupervised in an efficient, punctual and structured manner. To examine the outcomes of tasks and events, and judge levels of quality and importance
• Exploring - Able to investigate, research and consider alternatives
• Information retrieval - Able to access different and multiple sources of information
• Critical analysis & Problem Solving - Able to deconstruct and analyse problems or complex situations. To find solutions to problems through analyses and exploration of all possibilities using appropriate methods, rescources and creativity.

• Solve problems logically and systematically;
• Access and synthesize information and literature sources;
• Analyse and display data using appropriate methods and mathematical techniques;
• Demonstrate familiarity with relevant subject specific and general computer software packages.
• Knowledge and understanding of facts, concepts, principles & theories
• Use of such knowledge in modelling and design
• Problem solving strategies
• Knowledge and understanding of mathematical principles

Resource implications for students

N/A

Reading list

https://lucykuncheva.co.uk/PatternRecognitionTextbook.pdf

Compulsory in courses:

• G5BB: MSc Advanced Data Science year 1 (MSC/ADS)

Optional in courses:

• H117: MComp Computer Science year 4 (MCOMP/CS)
• G4AS: MSc Advanced Computer Science year 1 (MSC/ACS)