The module is about core technologies underpinning modern artificial intelligence. The module will introduce statistical machine learning and probabilistic modelling and their application to describing real-world phenomena. The module will give students a grounding in modern state of the art algorithms that allow modern computer systems to learn from data. It has a considerable focus on the mathematical underpinnings of key ML approaches, requiring some knowledge of linear algebra, differentiation and probability.

• Formal examination [50%] [LO1, LO2]
• Assignment [50%] [LO3, LO4]

• Blackboard
• Unconfirmed practical marks when available
• Exam Papers, past 2 years (where applicable)

• data science,
• machine learning.

By the end of the unit, a candidate will be able to demonstrate the ability to

1. understand probability theory and how it relates to uncertainty in modern artificial intelligence,
2. understand when and how to implement the appropriate learning paradigm for a given application,
3. implement a range of machine learning algorithms on simple problems,
4. deploy appropriate machine learning algorithms to solve real-world problems.

Typical content will include: 

• Introduction to machine learning
• End-to-End machine learning
• Linear regression
• Decision trees and ensemble methods
• Gaussian processes 
• Automatic differentiation
• Logistic regression
• Neural networks
• Unsupervised learning
• Deep generative models
• Other topics

It has a considerable focus on the mathematical underpinnings of key ML approaches, requiring some knowledge of linear algebra, differentiation and probability.