| CODE | ARI1204 | ||||||||||||||||
| TITLE | AI Numerical Methods 2 | ||||||||||||||||
| UM LEVEL | 01 - Year 1 in Modular Undergraduate Course | ||||||||||||||||
| MQF LEVEL | 5 | ||||||||||||||||
| ECTS CREDITS | 5 | ||||||||||||||||
| DEPARTMENT | Artificial Intelligence | ||||||||||||||||
| DESCRIPTION | This study-unit provides students with a deeper understanding of linear algebra and its relevance in Machine Learning. Basic concepts shall include advanced matrix and tensor operations together with the understanding of special types of matrices and vectors. Students will be able to work with various types of matrix decomposition and appreciate their relevance in different fields of machine learning. Study-unit Aims: - This study-unit aims to equip all students, regardless of their academic background, with the analytical knowledge necessary to be able to follow other study-units within the B.Sc. I.T. (Hons) in AI course. This unit aims to motivate students to value this scientific discipline and equip them with a level of mathematical literacy to understand better and contribute to the field of machine learning; - This study-unit will explain the importance of matrices and vectors in machine learning techniques. It will also demonstrate how different types of matrix decomposition are computed and their relevance to various AI techniques. Throughout this unit, students will also be introduced to applications of linear algebra in machine learning techniques. Learning Outcomes: 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - work with special kinds of matrices and vectors, including symmetric, diagonal, and orthogonal matrices; - work out various types of matrix decomposition; - solve systems of equations using matrix decomposition techniques; - compute the Moore-Penrose Pseudoinverse; - apply linear algebra to different machine learning techniques and applications. 2. Skills By the end of the study-unit the student will be able to: - analyse diverse problems using the right mathematical tools; - apply the acquired knowledge in linear algebra and calculus to compute solutions to problems. Main Text/s and any supplementary readings: Main Texts: - Deisenroth, M., Faisal, A., & Ong, C. (2020). Mathematics for Machine Learning. Cambridge: Cambridge University Press. doi:10.1017/9781108679930 - Strang, G. (2019) Linear Algebra and Learning from Data. Wellesley-Cambridge Press. Supplementary Readings: - Strang, G. (2016) Introduction to Linear Algebra. Wellesley-Cambridge Press. |
||||||||||||||||
| STUDY-UNIT TYPE | Lecture and Independent Study | ||||||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||||||
| LECTURER/S | Kristian Guillaumier |
||||||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2024/5. It may be subject to change in subsequent years. |
|||||||||||||||||