KV7006 - Machine Learning

You will learn through a combination of methods to support learning, including lectures, practical sessions in workshops and guided learning. Topics will normally be introduced in lectures and explored through practical exercises (helping you develop the required practical skills) and guided learning activities. You will be encouraged to develop independent self-learning skills and the development of critical analytic approaches for successfully applying machine learning to practical problem solving. More specifically, you will work in labs for improving your practical work. Tutors will support your learning through verbal feedback on your practical achievements. All module material will be available on the eLearning Portal (ELP) so that you can access information when you need to. The university library offers support for all students through its catalogue and an Ask4Help Online service.

Tutors will support you in the practical sessions, providing advice and feedback on your progress and engaging in discussion with you, to examine your ideas and those of others as your tutors value your input and opinions. You will be strongly encouraged to engage in further study by yourself or with other students outside class time to become an independent learner. This is an essential capability in every area of Computing, whose utility will long outlive the detail of current technical approaches.

This module will use and promote an eLP (Blackboard) based discussion forum. This will be configured to encourage you, other students and academic staff to participate in discussion about the subject matter of the module.

All modules at Northumbria include a range of reading materials that students are expected to engage with. Online reading lists (provided after enrolment) give you access to your reading material for your modules. The Library works in partnership with your module tutors to ensure you have access to the material that you need.

Knowledge & Understanding:

1. Demonstrate knowledge and understanding of the core concepts of machine learning and its underlying mathematical foundations

2. Demonstrate knowledge and understanding of the principal advanced machine learning techniques for solving real world problems

Intellectual / Professional skills & abilities:

3. Critically evaluate machine learning algorithms and applications

4. Analyse, design and develop machine learning solutions and evaluate their performance and evaluate the environmental and societal impact of these solutions and how to minimise their undesirable effects

Personal Values Attributes (Global / Cultural awareness, Ethics, Curiosity) (PVA):

5. Carry out independent research, individually and as part of a team, and communicate effectively the research findings

Formative Assessment
Formative assessment will take the form of practical tasks in workshop exercises. Feedback and guidance will be provided on these.

Summative Assessment
There will be two summative assessments.

1. For the first assessment, you will work in a group to write a review paper based on critical literature review of existing and emerging machine learning technologies and applications. This assignment will assess MLOs 2, 3 and 5, and is worth 40% of the module mark. Marks awarded to individual students will be based on peer assessment. The submission will be a written academic paper with a limit of (2000 to 2500 words).

2. For the second assessment, you will analyse, design and develop an appropriate solution to a given problem by selecting appropriate machine learning algorithms and tools. You will need to evaluate the performance of your solution and appropriately visualise the obtained results. This assignment will assess MLOs 1, 2, 3 and 4, and it is worth 60% of the module mark. Your submission will be in the form of a Python Notebook.

Feedback
Oral feedback will be provided on the formative assessment during the workshop sessions. Written feedback will be provided on the summative assessment.

None

None

The aim of this module is to give students the opportunity to study machine learning and how various machine learning techniques can been used to tackle realistic problems. Students will learn core concepts of machine learning, state-of-the-art techniques and research advances in this field. Students will also learn how to appropriately select from a range of machine learning techniques and tools to solve real world problems. Furthermore, students will learn how to critically evaluate different machine learning techniques , evaluate their performance and benchmark them against published findings.