Machining learning and artificial intelligence play more and more important roles in current engineering disciplines. This course will introduce the basics of machine learning and explore how such advanced techniques can be applied in the mechanical engineering field. Students will learn the art and science of Machine Learning from the fundamentals to state-of-the-art models. A strong emphasis is put on students learning the principles of engineering problem solving, and how these techniques can be used to tackle practical engineering problems. The students will complete the course with the confidence to explore these topics further and apply them to other areas of interest themselves.

Students should have some programming background to understand the course content. We will use Matlab as medium to implement the machine learning models.

Quantum computer can perform computations much faster than classical computer on certain type of problems, which starts a new page in computation history. Many problems that are intractable on classical computers may be tractable with the aid of quantum computing. This course will introduce the fundamental knowledge of superposition and entanglement to explain how a quantum computer bit (qubit) works. Famous quantum algorithms such as Shor’s algorithm for cryptography, Grover's algorithm for searching problem, variational quantum eigensolver for materials simulation, quantum Fourier transform algorithm for engineering mathematics…etc, all will be introduced in details. In advance, quantum machine learning is also been widely studied with success in computational applications. With these new tools and knowledge, quantum computers will become a powerful tool for our students to face the rapid changing challenges in this whole new era. 

For a student to pass the course, at least 30% of the maximum mark for both coursework and examination should be obtained.