Description

Machine Learning is one of the fundamental subjects in the field of Artificial Intelligence. Machine Learning is concerned with computer programs that automatically improve their performance through experience (e.g., learning to recognize image or speech, classify text documents, detect credit card frauds, or drive autonomous vehicles). This course covers both fundamental theory and practical algorithms for machine learning from a variety of perspectives. It includes a range of topics, from supervised learning (such as classification and regression) to unsupervised learning (such as clustering), and from traditional (shallow) learning (such as support vector machine) to recent state-of-the-art deep learning methods. The course is intended to prepare students for basic understanding of machine learning fundamentals and equip students with capability of applied machine learning techniques for real applications. Students are strongly encouraged to have proficiency in IS103 Computational Thinking prior to reading this course. NOTE: While this is an introduction course, it is a technical course and it is highly recommended that students are proficient in programming, probabilities, statistics and linear algebra (e.g., CS103 Linear Algebra for Computing Applications, CS105 Statistical Thinking for Data Science, CS201 Data Structures and Algorithms and CS202 Design and Analysis of Algorithms).

Learning Outcomes

Graduate Learning Outcomes

Disciplinary Knowledge, Multidisciplinary Knowledge, Interdisciplinary Knowledge, Critical thinking & problem solving, Understanding of sustainability issues

Competencies

Data Analytics, Computational Modelling, Data Engineering, Data Visualisation, Pattern Recognition Systems