Postgraduate taught 

Data Science MSc

Artificial Intelligence (M) COMPSCI5087

  • Academic Session: 2019-20
  • School: School of Computing Science
  • Credits: 10
  • Level: Level 5 (SCQF level 11)
  • Typically Offered: Semester 1
  • Available to Visiting Students: No
  • Available to Erasmus Students: No

Short Description

Artificial Intelligence (M) is an introduction to Artificial Intelligence, giving the students an overview of intelligent agent design. 

Timetable

3 hours per week

Requirements of Entry

For MSci students: Level 1 mathematics or equivalent; working knowledge of matrices, linear spaces and basic geometry. Fluency in a high-level programming language such as Java or Python. Data Fundamentals (H) or equivalent; working knowledge of vector spaces, numerical analysis/optimisation and probability.

 

For MSc students: acceptance into one of the MSc programmes listed in section 10 below.

Excluded Courses

Artificial Intelligence (H)

Co-requisites

Introduction to Data Science and Systems (M)

Programming and Systems Development (H)

Machine Learning for Data Scientists (M)

Assessment

Examination 80%; Continuous assessment- practical exercises 20%.

Main Assessment In: April/May

Course Aims

The aim of this course is to provide an overview of intelligent agent design, where agents perceive their environment and act rationally to fulfil their goals. Students will gain practical experience in labs, programming various aspects of intelligent systems.

Intended Learning Outcomes of Course

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

1. Demonstrate familiarity with the history of AI, philosophical debates, and understand the potential and limitations of the subject in its current form;

2. Explain the basic components of an intelligent agent, and be able to map these onto other advanced subjects such as information retrieval, computer vision, database systems, robotics, human-computer interaction, reactive systems, etc;

3. Discuss difficulties in computer perception;

4. Discuss basic issues in planning;

5. Explain and apply search-based problem-solving techniques;

6. Formulate and apply Bayesian networks in modelling and planning;

7. Explain and apply utility theory as a probabilistic framework for rational decision making;

8. Explain and apply basic machine learning techniques to learn from rewards and observations;

9. Discuss emerging and advanced machine learning techniques to learn from rewards and observations in high-dimensional planning problems (e.g. deep reinforcement learning, Monto Carlo tree-search, etc.)

Minimum Requirement for Award of Credits

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