The course is intended to extend the students' knowledge and skills, enabling them to critically engage with important advanced programming techniques (including Python) necessary for Machine Learning (ML). It will introduce the field of Artificial Intelligence (AI) with a focus on the foundations and practical applications of machine learning.

T.B.C.

None

None

Exam 35%, coursework 50%, Quiz 15%

The coursework cannot be redone because the feedback provided to the students after the original coursework would give any students redoing the coursework an unfair advantage. Students can resit the class test.

■ The course is intended to extend the student's knowledge to encompass a number of important advanced programming techniques necessary for Machine Learning. It will introduce the field of artificial intelligence with a focus on the foundations and fundamental applications of machine learning. The aims include:

■ To enhance and critically apply existing skills and practical processes for programming for data analysis (e.g., numpy and pandas from Python libraries)

■ To develop proficiency in common tools and techniques for data processing.

■ To acquire a critical understanding of the fundamental and basic concepts of Machine Learning and its role within the broader field of artificial intelligence

■ To engage with and critically evaluate practical applications of Machine Learning, e.g., using standard Python libraries.

By the end of the course students will be able to:

1. Demonstrate knowledge and proficient use of relevant modern programming environments and standard packages (e.g., Jupyter/Colab notebooks)

2. Design, implement, and critically assess effective and efficient programs for array and data processing using standard ML/AI packages.

3. Critically analyse fundamental concepts and principles of Machine Learning, including training/test data, data preprocessing, feature extraction, model fitting and evaluation.

4. Critically evaluate and compare computational process of learning from data in regression, classification and clustering.

5. Design, implement, and rigorously assess standard AI/ML algorithms for regression, classification and clustering.

6. Independently research, critically evaluate, and apply appropriate online resources (e.g., reference documentation for libraries).

Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.