Overview
Academic contacts
Offerings
Requisites
Other learning activities
Learning activities
Learning outcomes
Explain and compare the theories and algorithms behind machine learning models
Design and implement machine learning models using appropriate programming languages
Train, test and critically evaluate and compare the performance of machine learning models.
Apply best practices for data preparation and select appropriate data pre-processing techniques for different types of data.
Learn and use new programming and scripting languages independently, adapt to changing requirements and technologies.
Assessments
Additional information
The Unit will cover the following topics:
- Introduction, Overview, and Preliminaries
- Linear Neural Networks
- Multilayer Perceptrons
- Optimisation Algorithms
- Convolutional Neural Networks
- Recurrent Neural Networks
- Performance evaluation and best practices
- Applications: Computer Vision, Natural Language Processing, Recommender Systems. This may include one invited (industry) talk
- Wrap-up, summary, exam tips, and open discussions.
Each student is expected to read the lecture notes and any recommended reading materials relevant to the topic for each week. Students will be able to access the unit information and learning materials through LMS. A list of relevant reference texts and resources will be provided. Students will also need to spend some time doing the lab exercises for that week. In addition, each student will need to complete two assignments on their own, and sit for the final examination. Assignments may require independent research to be carried out by students. Students with demonstrated capability may have the possibility to work with real data sets that may be subject to confidentiality agreements.