Computing
Applied Machine Learning
Module code: G6061
Level 5
15 credits in spring semester
Teaching method: Lecture, Laboratory
Assessment modes: Coursework
In this module, you'll learn how machine learning learning methods can be applied to practical problems in different domains including natural language processing and computer vision.
We will discuss aspects such as:
• how different types of data can be effectively pre-processed.
• the mappings between problems and machine learning tasks and loss functions.
• system design considerations for different problems.
• metrics for evaluating the efficacy of predictions
As we work through a range of real-world applications, we will describe a variety of unsupervised and supervised machine learning models including classical machine learning tools and modern deep learning techniques. You'll be introduced to software packages to enable you to design and implement your own systems.
Pre-requisite
some programming experience
Module learning outcomes
- Determine the applicability of different machine learning models to data found in real-world applications.
- Propose designs for simple systems, including appropriate pre-processing, to solve practical problems using machine learning.
- Implement and document a computer program that learns and applies machine learning models to realistic data.
- Critically evaluate the efficacy of proposed systems and appropriately communicate this analysis.