Module COMP2261: ARTIFICIAL INTELLIGENCE

Department: Computer Science

COMP2261: ARTIFICIAL INTELLIGENCE

Prerequisites

• COMP1051 Computational Thinking AND (COMP1021 Maths for Computer Science OR MATH1551 Maths for Engineers and Scientists OR (MATH1561 Single Mathematics A AND MATH1571 Single Mathematics B) OR (MATH1061 Calculus I AND MATH1017 Linear Algebra I))

Corequisites

• None

Excluded Combination of Modules

• None

Aims

• To give students a fundamental understanding of some of the core problem-solving principles of Artificial Intelligence (AI) and the role of AI in societal applications.

Content

• AI Search: methods for solving hard real-world problems including general heuristic searches, such as various best-first searches and A* search, and local searches, such as hill-climbing, simulated annealing, genetic algorithms and other evolutionary algorithms, together with the practical application of these methods to problem solving.
• Ethics and Bias in AI: discussions on ethical considerations of AI applications in various disciplines, as well as algorithmic considerations regarding bias in AI. This can refer to human perspectives, leading to conversational explanations and explainable AI, as well as new algorithmic solutions, such as eliminating bias induced by overlapping training/test set or sensitivity analysis.
• Machine Learning: types of machine learning systems; challenges of machine learning; testing and validating; machine learning workflow; classification; training models; support vector machines; decision trees; ensemble learning and random forests; dimensionality reduction; clustering; Gaussian mixtures; introduction to neural networks and deep learning.

Learning Outcomes

• The key principles and methodologies of search in an AI context where the problems to be solved are computationally hard (AI Search).
• The key principles of ethical concerns and bias in AI for real-world applications, from an accountability perspective and as regards the application of algorithms (Ethics and Bias in AI).
• The key principles of machine learning for use in managing datasets and building models and core methodologies in relation to managing data and training models (Machine Learning).

• An ability to implement generic artificial intelligence search techniques, together with an ability to critically evaluate and fine tune the resulting programs (AI Search).
• An ability to discuss implications of AI solutions in real-world applications and on applying sensitivity analysis to given data (Ethics and Bias in AI).
• An ability to manage data and to select and apply appropriate algorithms to recognise patterns within the data, together with an ability to implement, analyse and compare learning algorithms (Machine Learning).

• An ability to undertake reasoning in relation to AI problem-solving and AI applications.
• An ability to communicate technical information.
• An ability to appreciate societal impact of AI.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

• Lectures enable students to learn core material on the different subject areas.
• Practical classes enable students to apply the material learned in lectures and enhance their understanding.
• Formative and summative assignments encourage and guide independent study, and test the knowledge acquired and the students' ability to use this knowledge to solve problems.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

Example formative exercises given during the course.

■ Attendance at all activities marked with this symbol will be monitored. Students who fail to attend these activities, or to complete the summative or formative assessment specified above, will be subject to the procedures defined in the University's General Regulation V, and may be required to leave the University