Course overview
This course is about extracting useful information from visual data, and developing learning algorithms that combine diverse datasets (e.g., images, text, etc) to improve models. It covers the fundamental mathematics for the underlying data structures and algorithms, as well as implementation and applications to real-world datasets.
- Mathematical Foundations of Computer Vision
- Deep Learning for Computer Vision
- Applications of Computer Vision and Multimodality
Course learning outcomes
- Describe modern computer vision techniques and connect it with the underlying mathematical principles
- Explain how deep learning is used to solve problems in computer vision including rational decision making throughout the modelling process.
- Demonstrate skills in deploying computer vision using computer programming of both traditional and modern techniques
- Apply mathematical techniques as well as machine learning to solve a variety of problems related to computer vision at an appropriate level of difficulty
- Effectively communicate computer vision concepts including interpretability and uncertainty using mathematics, statistics and visualisation