Last modified: 11 Aug 2025 12:16
This course will deliver the most sophisticated Machine Learning methodologies and algorithms which would be illustrated across a wide range of applications including but not limited to images, videos, health, time series data, language processing, etc. This course provides students with the Machine Learning principles for continuing learning and working in the area of Data Science and Artificial Intelligence.
| Study Type | Postgraduate | Level | 5 |
|---|---|---|---|
| Term | First Term | Credit Points | 15 credits (7.5 ECTS credits) |
| Campus | Aberdeen | Sustained Study | No |
| Co-ordinators |
|
||
This course will present advanced Machine Learning principles with applications. Practical will help students to understand principles applying to real-world applications using cutting-edge tools and libraries. The lectures will cover supervised learning, unsupervised learning, and as well as reinforcement learning. This will include regression and classification models, stochastic gradient descent algorithms, automatic differentiation, deep neural networks, model assessment and selection, model evaluation, generative adversarial networks, reinforcement learning, unsupervised learning models.
Information on contact teaching time is available from the course guide.
| Assessment Type | Summative | Weighting | 50 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback | ||||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Conceptual | Understand | Have knowledge and understanding of fundamentals of machine learning, including a range of popular machine learning algorithms. |
| Procedural | Analyse | Be able to critically examine the strengths and limitations of common machine learning algorithms when solving a specific problem. |
| Procedural | Apply | Be able to perform data pre-processing for machine learning. |
| Procedural | Apply | Be able to use existing machine learning tools, frameworks, and libraries to build solutions for real-world or benchmark problem solving. |
| Reflection | Create | Be able to write reports for machine learning solutions. |
| Assessment Type | Summative | Weighting | 50 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Word Count: 2000 |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Conceptual | Understand | Have knowledge & understanding of the core concepts of, and common practices, in Machine Learning. |
| Conceptual | Understand | Have knowledge and understanding of fundamentals of machine learning, including a range of popular machine learning algorithms. |
| Procedural | Analyse | Be able to critically examine the strengths and limitations of common machine learning algorithms when solving a specific problem. |
| Procedural | Apply | Be able to perform data pre-processing for machine learning. |
| Procedural | Apply | Be able to use existing machine learning tools, frameworks, and libraries to build solutions for real-world or benchmark problem solving. |
| Procedural | Evaluate | Be able to systematically evaluate the built machine learning solutions. |
| Reflection | Create | Be able to write reports for machine learning solutions. |
There are no assessments for this course.
| Assessment Type | Summative | Weighting | ||
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback | ||||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Conceptual | Understand | Have knowledge & understanding of the core concepts of, and common practices, in Machine Learning. |
| Conceptual | Understand | Have knowledge and understanding of fundamentals of machine learning, including a range of popular machine learning algorithms. |
| Procedural | Apply | Be able to use existing machine learning tools, frameworks, and libraries to build solutions for real-world or benchmark problem solving. |
| Procedural | Apply | Be able to perform data pre-processing for machine learning. |
| Procedural | Evaluate | Be able to systematically evaluate the built machine learning solutions. |
| Procedural | Analyse | Be able to critically examine the strengths and limitations of common machine learning algorithms when solving a specific problem. |
| Reflection | Create | Be able to write reports for machine learning solutions. |
We have detected that you are have compatibility mode enabled or are using an old version of Internet Explorer. You either need to switch off compatibility mode for this site or upgrade your browser.
