Module ENGI47615: Optimisation and Control for Artificial Intelligence

Department: Engineering

ENGI47615: Optimisation and Control for Artificial Intelligence

Prerequisites

Corequisites

• As specified in programme regulations.

Excluded Combination of Modules

• As specified in programme regulations.

Aims

• To understand optimisation and control techniques that can be used to improve AI-driven engineering systems.
• To give students the tools and training to recognize and formulate optimisation and control problems that arise in AI applications.
• To present the basic theory of such problems, concentrating on results that are useful in AI-driven applications and computation.
• To give students a thorough understanding of how such problems are solved in AI contexts, and practical experience in solving them.
• To provide students with the background required to use optimisation and control methods in their own AI research work or applications.

Content

• Optimisation theory and techniques for AI applications.
• Model Predictive Control (MPC) theory and implementation.
• Applications of optimisation and MPC in AI-driven engineering systems.
• Integration of machine learning techniques with optimisation and control.

Learning Outcomes

• A knowledge and understanding of optimisation and control theory and techniques as applied to AI-driven systems.
• AHEP4 Learning Outcomes: In order to satisfy Professional Engineering Institution (PEI) accreditation requirements the following Accreditation of Higher Education Programmes (AHEP4) Learning Outcomes are assessed within this module:
• M1. Apply a comprehensive knowledge of mathematics, statistics, natural science and engineering principles to the solution of complex problems (assessed by an In-Class Test).

• An awareness of current analysis methods in AI optimisation and control along with the ability to apply those methods in novel situations.
• An in-depth knowledge and understanding of specialised and advanced technical skills in AI-driven optimisation and control, an ability to perform critical assessment and review, and an ability to communicate the results of their own work effectively.

• Capacity for independent self-learning within the bounds of professional practice in AI and engineering.
• Highly specialised numerical and computational skills appropriate to an AI engineer.
• Mathematics relevant to the application of advanced AI concepts in engineering optimisation and control.

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

• The Optimisation module is covered in lectures, and reinforced by problem sheets, leading to the required problem solving capability.
• Two hour lectures delivered in a single term, structured as one lecture of methods followed by one lecture of exercises. The methodology taught in the first hour would be immediately followed by a second hour of exercises to consolidate student knowledge and understanding of optimisation theory and techniques.
• Students are encouraged to make use of staff 'Surgeries' to discuss any aspect of the module with teaching staff on a one-to-one basis. These are sign-up sessions available for up to one hour per week.
• Students will be required to submit formative problem sheets throughout the academic year into the virtual learning environment to check their understanding as the course progresses.
• Students will be formed into study groups and will attend timetabled Discussion Classes (up to a maximum of two) during the term.
• At the start of the academic year, a benchmark test will be administered to gauge students' understanding and direct them to further study as appropriate.
• A mock exam will take place in the Epiphany term. This will provide students with an exam-type experience in a formative setting and allow them to discuss their performance with a member of the academic staff.
• The module will be assessed by an In-Class Test which will take place in the Easter term. An In-Class Test is appropriate because of the wide range of analytical, in-depth material covered in this module and allow students to demonstrate the ability to solve advanced problems independently as well as that they have deeply engaged with the material.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

Formative assessment is provided by means of compulsory formative problem sheets, benchmark test and mock examinations. Formative benchmark test scheduled to take place during Induction Week. To note, all formative assessments are compulsory.

■ 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