A basic introduction to the field of artificial intelligence focusing on an introduction to the foundations of machine learning, based around a series of practical case studies using data from a range of research areas.

Two lecture hours per week; Two lab hours per week.

None

Programming and Systems Development (H)

Examination 60%; Coursework 40%. The coursework comprises analysis of real data arising from two case studies.

To present students with an introduction to the field of artificial intelligence giving the students an overview of intelligent agent design with focus on machine learning with application to data science.

The course will present the context and history of AI and present the general theory of learning from data and decision making presented in the context of popular Machine Learning methods.

The module is focussed on practical application of AI and Machine Learning techniques from standard libraries (e.g. scikit-learn) in a variety of domains as well as providing good practice in training and validating Machine Learning models.

The course will include practical AI/ML case studies from e.g. Human Computer Interaction, Information Retrieval, Bioinformatics and Computer Vision and Graphics.

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

1. Demonstrate familiarity with the history of artificial intelligence and machine learning, ethical and philosophical debates, and understand the potential and limitations of the subject in its current form;

2. Explain the computational process of learning from data for example regression, classification, clustering and decision-making problems. 

3. Explain and demonstrate the strengths and weaknesses of common algorithms and propose appropriate choices for specific problems;

4. Analyse and formulate a learning problem as an optimisation problem and discuss the impact of the choice of loss function;

5. Demonstrate knowledge of the major artificial and machine learning application areas in, for example Physics, Information Retrieval, Human Computer Interaction, Bioinformatics and Computer Vision & Graphics;

6. Implement, customise and apply AI/ML algorithms in Python using existing libraries (e.g. scikit-learn) to regression, classification, clustering, probability density estimation and dimensionality reduction;

7. Demonstrate proficiency in the data-driven modelling process from data collection to decision-making (be able to setup a machine learning project, organise data and code, develop and apply a model, visualise and analyse the results, and communicate them in a coherent document). 

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