FIT2111 · Symbolic artificial intelligence and machine learning

Overview

This unit covers the concepts of intelligent agents and delves into problem-solving and search techniques, including problem representation, heuristic search, and adversarial search. You will learn about knowledge representation and reasoning, focusing on propositional and first-order logic for AI applications, as well as planning. You will also engage with a variety of machine-learning techniques, including data representation, unsupervised and supervised learning and reinforcement learning. The curriculum also addresses the selection of appropriate model complexity tailored to specific problems and datasets. Through problem-based learning activities, you will apply these techniques to real-world scenarios and examine ethical considerations in AI.

Offerings

The Handbook publishes no offerings for this unit.

Assessment

The Handbook publishes no assessment items for this unit yet.

Assessment details may change. Please refer to the assessment information in Moodle closer to the start of the teaching period.

Requisites

Learning outcomes

1. Design and develop intelligent systems using computational methods for searching, problem-solving, reasoning, and knowledge representation;
2. Apply machine learning techniques, including data representation, clustering, factor analysis, and classification, to solve complex problems;
3. Assess and select appropriate model complexities for different datasets and problem scenarios, ensuring optimal performance and accuracy;
4. Analyse and address real-world problems through problem-based learning activities, utilising advanced machine learning and computational intelligence techniques;
5. Understand the practical and ethical implications of Artificial Intelligence in real-world contexts.

Workload

No workload detail published.

Student experience, not official rules. Nothing here changes what the Handbook says.