In this module you learn what is meant by machine learning and how to explain the key algorithms (especially the backpropagation algorithm for learning deep neural networks) and mathematical equations that underlie them. You also familiarise yourself with a range of machine learning algorithms and their inner mechanisms. Using state-of-the-art software technology apply these algorithms to the solution of problems. You will study the existing machine learning implementations of selected algorithms, and you will also engage in implementation of algorithms and procedures relevant to machine learning.
Private Study: 111
Contact Hours: 39
Total: 150
13.1 Main assessment methods
Two simulation assessments (individual; 12 hours; 20% total)
Examination (2 hours; 80%)
Reassessment methods
Like for like
The most up to date reading list for each module can be found on the university's reading list pages.
On successfully completing the module students will be able to:
8.1 Describe what is meant by machine learning, list a number of types of machine learning algorithms (e.g. neural networks) and give a brief description of each together with some examples of their (actual or potential) applications.
8.2 Select the appropriate machine learning paradigm for a particular problem and be able to justify this choice based on knowledge of the properties and potential of this paradigm. To be able to compare the general capabilities of a number of such paradigms and give an overview of their comparative strengths and weaknesses.
8.3 Explain the mathematical equations that underlie selected machine learning algorithms, both the equations/ algorithms that define predictions or decisions, and those that define learning (e.g. the backpropagation algorithm for neural networks).
8.4 Analyse learning phenomena from the point of view of their being computational systems. To be able to take these phenomena and identify the features which are important for computational problem solving by learning from data or from simulation.
8.5 Build machine learning models (e.g. neural networks) using state-of-the-art simulation technology and apply them to the solution of problems. In particular, to select from the canon of learning algorithms which is appropriate for a particular problem domain.
8.6 Discuss examples of challenges related to learning from data. To be able to analyse related systems not directly studied in the course in a similar fashion.
8.7 Discuss examples of machine learning models as applied to various tasks.
The intended generic learning outcomes.
On successfully completing the module students will be able to:
9.1 Utilize the library, exploit online resources and internet sites to support investigations into these areas.
9.2 Improve their analytical skills in respect of subsymbolic systems.
9.3 Enhance their time management and organisation skills.
9.4 Learn effectively for the purpose of continuing professional development.
University of Kent makes every effort to ensure that module information is accurate for the relevant academic session and to provide educational services as described. However, courses, services and other matters may be subject to change. Please read our full disclaimer.
