Modelling and Analysis for AI (ELEN90097)

This subject builds up the fundamentals for modelling dynamical systems, with a key focus on the aspects and decisions of modelling that are relevant for the application of AI and data-intensive learning methods. The discussion and evaluation of modelling methods focuses on how model fidelity influences simulation-to-real transfer; how modelling and simulation decisions influence computation time required for training and validation; and how discrete-time models introduce complexity when representing continuous-time engineering systems. Subsequently, it introduces the basic principles and engineering applications of programming and data structures in a condensed form with a project-centric pedagogy.  It covers the fundamentals of databases and data structures, basic algorithms, scientific programming, and classic AI problem solving. It will focus specifically on engineering problems from multiple application areas including Internet of Things (IoT), smart grid and power systems, robotics, cyber-security, and communication networks. The concepts taught in this subject will lead to a better understanding of how programming and databases play a role in modern engineering and cyber-physical systems.

INDICATIVE CONTENT
Topics covered may include:

• Models for engineering systems in multiple disciplines, including analysis of what makes the models amenable to AI and data-intensive learning methods.
• Principles for simulating dynamic systems that are most relevant for the use of AI methods and to address these principles with existing software tools.
•  Scientific programming for modelling using Python programming language and libraries such as scipy and numpy.
• Engineering data structures and time series data and their storage in SQL and noSQL databases.

Example engineering applications will be taught via projects in areas such as Internet of Things (IoT), smart grid and power systems, robotics, cyber-security, and communication networks.