2015/16 Taught Postgraduate Module Catalogue
COMP5830M Knowledge Representation and Machine Learning
15 creditsClass Size: 30
Module manager: Professor Tony Cohn
Email: a.g.cohn@leeds.ac.uk
Taught: Semester 1 (Sep to Jan) View Timetable
Year running 2015/16
This module is not approved as an Elective
Module summary
How can we get computers to learn, represent knowledge and reason with it? This module covers the fundamental principles of knowledge representation and machine learning. You will learn about some of key algorithms used in Automated Reasoning and Machine Learning and use software tools to compute inferences by Automated Reasoning and to build models from data using Machine Learning algorithms.Objectives
On completion of this module, students should be able to:- understand the fundamental principles of Knowledge Representation and Machine Learning,
- analyse informal descriptions of moderately complex real world scenarios in terms of appropriate formal Knowledge Representation languages,
- understand some of the key algorithms used in Automated Reasoning and Machine Learning,
- appreciate the power and limitations of different approaches and algorithms for Automated Reasoning and Machine Learning,
- use software tools to compute inferences by Automated Reasoning and to build models from data using Machine Learning algorithms.
Learning outcomes
On completion of the year/programme students should have provided evidence of being able to:
-to demonstrate in-depth, specialist knowledge and mastery of techniques relevant to the discipline and/or to demonstrate a sophisticated understanding of concepts, information and techniques at the forefront of the discipline;
-to exhibit mastery in the exercise of generic and subject-specific intellectual abilities;
-to demonstrate a comprehensive understanding of techniques applicable to their own research or advanced scholarship;
-proactively to formulate ideas and hypotheses and to develop, implement and execute plans by which to evaluate these;
-critically and creatively to evaluate current issues, research and advanced scholarship in the discipline.
Syllabus
Review of logical foundations of knowledge representation including key properties of formal systems (such as soundness, completeness, expressiveness and tractability).
Representing and reasoning about time, actions and physical changes (e.g. interval calculus, event calculus). Representing space and physical situations (topology, orientation, physical objects).
Reasoning in the presence of vagueness and uncertainty.
Automated inference techniques (e.g. resolution, relational composition, non-monotonic reasoning, logic programming).
Techniques for machine learning (e.g. decision trees, Bayesian networks, instance-based learning, kernel machines, clustering, inductive logic programming).
Examples will be drawn from a variety of Artificial Intelligence application areas, such as: robot control, AI for computer games, machine language understanding and computer vision.
Teaching methods
Delivery type | Number | Length hours | Student hours |
Laboratory | 11 | 1.00 | 11.00 |
Lecture | 22 | 1.00 | 22.00 |
Private study hours | 117.00 | ||
Total Contact hours | 33.00 | ||
Total hours (100hr per 10 credits) | 150.00 |
Opportunities for Formative Feedback
Coursework and labs.Methods of assessment
Coursework
Assessment type | Notes | % of formal assessment |
Assignment | Coursework | 40.00 |
Total percentage (Assessment Coursework) | 40.00 |
This module is re-assessed by exam only.
Exams
Exam type | Exam duration | % of formal assessment |
Open Book exam | 2 hr | 60.00 |
Total percentage (Assessment Exams) | 60.00 |
This module is re-assessed by exam only.
Reading list
The reading list is available from the Library websiteLast updated: 05/11/2015
Browse Other Catalogues
- Undergraduate module catalogue
- Taught Postgraduate module catalogue
- Undergraduate programme catalogue
- Taught Postgraduate programme catalogue
Errors, omissions, failed links etc should be notified to the Catalogue Team.PROD