- Department: Computer Science
- Credit value: 20 credits
- Credit level: M
- Academic year of delivery: 2023-24
- See module specification for other years: 2024-25
This is a compulsory 20 credit module available to MSc AI students. It is required to run in the first semester as it provides prerequisites for several follow-on modules in semester 2 (e.g. PADL and AIPS).
This module will begin by revising and extending fundamental skills and knowledge in programming, algorithms, data processing, and discrete and continuous mathematics that are required for further study in AI. While students will have covered some of this material to varying extents and depths during their undergraduate studies, we require that all students have the same solid foundation of knowledge and skills across all topics. This module will then introduce the philosophical and ethical basis of intelligence and AI, the different paradigms of AI, and basic symbolic, statistical and learning-based AI approaches.
Occurrence | Teaching period |
---|---|
A | Semester 1 2023-24 |
This module lays the foundation for advanced study in symbolic, statistical and learning-based approaches to artificial intelligence. It revises and extends fundamental skills and knowledge in programming, algorithms, data processing, and discrete and continuous mathematics, all from the perspective of their use in AI. It introduces the philosophical and ethical basis of intelligence and AI, the different paradigms of AI and some basic approaches within these paradigms. Practical work will involve both mathematical exercises and programming in Python.
By the end of this module, students will be able to:
Explain basic philosophical arguments and categorisations relating to notions of intelligence, computation and artificial intelligence
Distinguish between symbolic and learning-based AI and between supervised and unsupervised learning
Implement data preprocessing pipelines in Python for collecting, transforming, preparing and cleaning data for purposes of analysis
Represent knowledge using propositional and first order logic
Compute partial derivatives and solve systems of linear equations using linear algebra
Solve regression and classification problems with one variable or multiple variables using linear and logistic regression
Apply the gradient descent algorithm to optimise multivariate functions
Construct a basic neural network and optimise its weights using backpropagation
Task | % of module mark |
---|---|
Online Exam -less than 24hrs (Centrally scheduled) | 100 |
None
Task | % of module mark |
---|---|
Online Exam -less than 24hrs (Centrally scheduled) | 100 |
Feedback is provided through work in practical sessions, formative assessments, and after the final assessment as per normal University guidelines.
To be added.