FIT2111 · Symbolic artificial intelligence and machine learning

Overview

Intelligent systems need more than models; they need ways to represent problems, reason about possible actions, learn from data, and make decisions responsibly. This unit develops core artificial intelligence capability by combining symbolic artificial intelligence, search, reasoning, planning and machine learning within real-world problem contexts. You will learn how intelligent agents represent states, goals, constraints and decision processes, and how techniques such as heuristic search, adversarial search, knowledge representation, propositional and first-order logic, and planning support intelligent behaviour. You will also work with machine learning methods, including data representation, supervised learning, unsupervised learning and reinforcement learning, with attention to model complexity, performance, generalisation and suitability for different problems and datasets. Through problem-based learning activities, you will apply artificial intelligence methods and tools to analyse, design, implement and evaluate intelligent systems for complex scenarios. The unit also develops your ability to reason about the ethical, privacy, security and societal implications of artificial intelligence, and to make responsible choices when selecting, applying and evaluating artificial intelligence techniques.

Offerings

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. Select and apply artificial intelligence methods and tools for search, reasoning, planning and intelligent decision-making in complex computational contexts;
2. Analyse and formulate complex artificial intelligence problems by representing states, goals, constraints, uncertainty and decision processes to support effective solution strategies;
3. Analyse and formulate complex artificial intelligence problems by representing states, goals, constraints, uncertainty and decision processes to support effective solution strategies;
4. Design, configure and evaluate artificial intelligence system components that integrate symbolic reasoning, search, planning and machine learning techniques for defined intelligent behaviour;
5. Design, train, tune and evaluate machine learning models with appropriate attention to model complexity, performance, generalisation and suitability for problem and context characteristics;
6. Evaluate ethical, privacy, security and societal implications of artificial intelligence systems, and justify responsible choices in their design, application and evaluation.

Workload

Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled online and face to face learning activities and independent study. Independent study may include associated reading and preparation for scheduled teaching activities.

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