CS3AM: Artificial Intelligence and Machine Learning

Module code: CS3AM

Module provider: Computer Science; School of Mathematical, Physical and Computational Sciences

Credits: 20

Level: 6

When you’ll be taught: Semester 1

Module convenor: Dr Muhammad Shahzad , email: m.shahzad2@reading.ac.uk

Pre-requisite module(s): BEFORE TAKING THIS MODULE YOU MUST ( TAKE CS1MA20 OR TAKE CS1MA20NU ) AND ( TAKE CS2DA OR TAKE CS2AO17 ) OR ( TAKE CS2DANU OR TAKE CS2AO17NU ) AND ( TAKE CS2PP OR TAKE CS2PP22 OR TAKE CS2PP22NU ) (Compulsory)

Co-requisite module(s):

Pre-requisite or Co-requisite module(s):

Module(s) excluded:

Placement information: NA

Academic year: 2025/6

Available to visiting students: Yes

Talis reading list: Yes

Last updated: 24 April 2025

Overview

Module aims and purpose

The main goal of this module is to familiarise students with both the foundational and advanced concepts in Artificial Intelligence (AI) and Machine Learning (ML). Specifically, the module shall cover adversarial search, game theory, and learning methodologies including both shallow/conventional (e.g., Naïve Bayes, Decision Trees, Multilayer Perceptrons etc.), ensemble (Bagging and Boosting) and deep learning (Convolutional Neural Networks and Recurrent Neural Networks for both National Language Processing and Vision) methods. The application of these methods shall be demonstrated over variety of real-world problems including classification, regression, predictive modelling, information extraction, and signal (vision/speech) processing. 

Module learning outcomes

By the end of the module, it is expected that students will be able to:

1. Explain the foundational theory and advanced concepts underpinning Artificial Intelligence (AI)
2. Discuss and differentiate wide variety of AI algorithms and techniques
3. Apply a variety of learning algorithms to a given data
4. Evaluate various learning algorithms for optimal model selection
5. Employ modern tools and frameworks to address a real-world problem in a small-scale AI project and demonstrate the practical skills in the field
6. Demonstrate their abilities in critical thinking to solve a large problem integrating components of data engineering, algorithm development and implementation
7. Demonstrate their abilities in professional and effective writing for algorithm development and software implementation

Module content

The module covers the following topics:

• Introduction to AI and ML concepts (Bias Variance Trade Off, Overfitting, Regularization) Supervised Learning (Regression/Classification)
• Linear/Logistic Regression
• Shallow machine learning methods (Decision Trees and Random Forests
• Data Clustering(K-means)
• Deep Neural Networks Architectures, Training and Hyper Parameter Tuning
• Convolutional Neural Networks
• Recurrent Neural Networks and their applications
• Unsupervised Learning (Generative AI)
• Ethical aspects and risks/safety of AI systems
• Artificial Agents, Adversarial Search, and Game Theory
• Reinforcement Learning

Structure

Teaching and learning methods

The module consists of 2-hour lectures and 2-hour practical sessions per week. The lectures will introduce students the theories, concepts and underpinning principles specified in the indicative content while the supervised practical sessions will guide them to develop thorough understanding in implementing AI algorithms for variety of different tasks. The formal lecture and practical sessions will enable students to apply the fundamental AI & ML techniques to solve a given problem, by demonstrating using programming, analysis and report writing. Moreover, these sessions will be supplemented with several forms of digital resources to support learning. The summative assessment consists of one piece of individually written coursework assignment which requires every student to demonstrate his/her achievement in de