A basic introduction to the field of Artificial Intelligence with a focus on the foundations of machine learning to solve engineering problems 

■ 1 x 2h introduction to the course

■ 9 x 2 x 1h technical lectures 

■ 6 x 1h tutorial

■ 2 x 2h demonstration

■ 1 x 2h lecture on societal impact of AI

None

None

50% continuous assessment delivered as 4 practical assessments in weeks 2,3,7,8 of the course, weighting 10%, 10%, 15%, 15% respectively (multiple choice and coding questions on Moodle). 50% set exercise delivered as 2 sessions in weeks 5 and 10 weighting 20% and 30% respectively (analysis of real data obtained from 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.

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 the application of AI and Machine Learning techniques to engineering problems. The students will be introduced to the use of standard libraries 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.

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

■ demonstrate familiarity with the history of artificial intelligence and the philosophical debate on the limitations and potential of AI in its current form;

■ critically discuss the ethical implications of AI, its societal, ethical and technical sustainability;

■ explain the computational process of learning from data for example regression, classification, clustering and decision-making problems;

■ explain and demonstrate the strengths and weaknesses of common algorithms and propose appropriate choices for specific problems;

■ recognise and summarise key aspects of the major artificial and machine learning application areas in, for example, image processing, information retrieval, human-computer interaction;

■ implement, customise and apply AI/ML algorithms in Python using existing libraries (for example scikit-learn) to regression, classification, clustering, probability density estimation and dimensionality reduction;

■ show 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.