Statistics for Artificial Intelligence II - MAT00127M
- Department: Mathematics
- Credit value: 20 credits
- Credit level: M
- Academic year of delivery: 2025-26
Module summary
This module will cover state of the art methods in Artificial Intelligence and analyse these methods from a statistical point of view.
Related modules
Pre-requisite Modules
Statistics for Artificial Intelligence I
Module will run
| Occurrence | Teaching period |
|---|---|
| A | Semester 2 2025-26 |
Module aims
This module will cover state of the art methods in Artificial Intelligence and analyse these methods from a statistical point of view.
Module learning outcomes
By the end of the course, students will have an advanced understanding of many aspects of Machine Learning, and in particular how it can be used in mathematical data science. Specifically, students will be able to:
-
Demonstrate working understanding of data complexity measures
-
Use advanced data analysis techniques from machine learning, such as Stochastic Gradient Descent and Kernel methods
-
Demonstrate understanding of the theoretical and practical implementation of ideas from deep learning and deep neural networks
-
Demonstrate working understanding and use of generative models in the context of machine learning, including their advantages and shortcomings
Module content
-
Overfitting, complexity measures, Rademacher complexities
-
Stochastic Gradient Descent
-
Kernel methods
-
Deep learning and deep neural networks
-
Practical Deep learning with Keras and Python
-
Generative models and diffusions
-
Reinforcement learning
Indicative assessment
| Task | % of module mark |
|---|---|
| Closed/in-person Exam (Centrally scheduled) | 100.0 |
Special assessment rules
None
Indicative reassessment
| Task | % of module mark |
|---|---|
| Closed/in-person Exam (Centrally scheduled) | 100.0 |
Module feedback
Current Department policy on feedback is available in the student handbook. Coursework and examinations will be marked and returned in accordance with this policy.
Indicative reading
-
Bach, F (2024). Learning theory from first principles. MIT Press.
-
Shalev-Shwartz, S. and Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press.
-
Szepesvari, C (2009). Algorithms for Reinforcement Learning. Morgan & Claypool Publishers.
-
Chollet, F. (2021). Deep Learning with Python, 2nd Edition. Manning Publications.