Last modified: 22 May 2019 17:07
This course presents the fundamental as well as the most popular Machine Learning theories and algorithms, used in a wide range of applications such as classification, prediction, regression, and those are core to the design of for instance computer Go player AlphaGo. This course provides the building blocks for understanding and using Machine Learning techniques and methodologies and prepares students to work in data science and general AI systems.
|Session||First Sub Session||Credit Points||15 credits (7.5 ECTS credits)|
|Campus||Old Aberdeen||Sustained Study||No|
The course will present the theory and practice of Machine Learning, including the state-of-the-art in tools, libraries, techniques and environments. Lectures will cover key concepts, mechanisms and results, with exercises in practicals/tutorials for individuals and teams to explore practical aspects. This will include: Machine learning problems (e.g. clustering, classification, concept/model learning); Symbolic machine learning (e.g. Support vector machines, reinforcement learning, inductive and analytical learning); Statistical machine learning (e.g regression, Bayesian learning, parametric density estimation); Bio-inspired learning (e.g. Neural nets & deep learning, evolutionary computing).
Information on contact teaching time is available from the course guide.
Individual Project (50%); Individual Project (50%).
Resit: where a student fails the course overall they will be afforded the opportunity to resit those parts of the course that they failed (pass marks will be carried forward).
There are no assessments for this course.
Formative feedback for in-course assessments will be provided in written form. Additionally, formative feedback on performance will be provided informally during practical sessions.