The University of Sheffield
School of Computer Science

COM318 Foundations and Applications of AI

Summary This module will provide the mathematical and statistical underpinnings for artificial intelligence, some of which are used more widely in computer science, and look at some practical applications of AI, with a focus on data science. Semester 1 will focus on the mathematical and statistical underpinnings, including probability, random variables and distributions (both discrete and continuous), finite sample spaces, Bayes rule, sampling, hypothesis testing, the law of large numbers, the central limit theorem and linear regression. Semester 2 will provide an introduction to practical data science. Topics include: data preprocessing, feature extraction, feature selection, and supervised/unsupervised learning. The module will employ a practical Python-based approach to help students develop an intuitive grasp of the sophisticated mathematical ideas that underpin this challenging but fascinating subject. 
Session Academic Year 2026/27
Credits 20
Assessment

Assignment

Formal Examinations
Lecturer(s) Xingyi Song, Nikita Toropov & Maksim Zhukovskii
Resources
Aims This unit aims to:
  • Introduce students to the probabilistic tools and techniques commonly used in Computer Science
  • Develop the understanding of the main ideas behind statistical modelling 
  • Teach students to estimate parameters of statistical models and perform statistical inference;
  • Provide an accessible introduction to key concepts in artificial intelligence (AI) and pattern processing.
  • Demonstrate the application of AI in a number of recent research areas 
  • Develop an appreciation of the difficulties involved when trying to extract meaning from naturally occurring data with particular reference to data preprocessing, feature extraction, classifier design and efficient learning
  • To prepare students for specialised AI subjects at level 3/4, such as natural language processing, speech processing, computer vision and computational biology
Learning Outcomes 

By the end of the module the student will be able to:  

  1. Apply probabilistic and statistical techniques that are the foundations of artificial intelligence.
  2. Appraise the underlying principles of data science algorithms and techniques to determine an appropriate one for a specified problem.
  3. Implement computer programs using various data science algorithms and techniques to solve practical problems.
  4. Evaluate the performance of data science algorithms and techniques.
Content

This module will cover:

  • Probability, sample space, events, probability space
  • Random variables and random vectors
  • Discrete and continuous distributions and their characteristics: expectation and variance
  • Conditional probability, conditional expectation, conditional distribution 
  • Convergence and limit theorems 
  • Statistical models and parameters 
  • Point and interval estimation 
  • Hypothesis testing 
  • Estimation and inference in linear regression
  • Classification, including Bayes decision theory
  • Non-parametric classifiers, including nearest-neighbour classifier
  • Feature selection
  • Feature generation
  • Introduction to deep learning and neural networks
  • Unsupervised learning and clustering
Restrictions Cannot be taken with COM226.
Teaching Method Lectures, Tutorials and Laboratory Classes.
Feedback Feedback following the assignment and during labs/lectures for weekly formative exercise questions.