| CODE | ICS2207 | ||||||||||||
| TITLE | Machine Learning: Introduction to Classification, Search and Optimisation | ||||||||||||
| UM LEVEL | 02 - Years 2, 3 in Modular Undergraduate Course | ||||||||||||
| MQF LEVEL | 5 | ||||||||||||
| ECTS CREDITS | 5 | ||||||||||||
| DEPARTMENT | Artificial Intelligence | ||||||||||||
| DESCRIPTION | PART ONE – Introduction to Classification, Search and Optimisation This study-unit will introduce techniques in Machine Learning and includes an introduction to Inductive, Deductive, Supervised and Unsupervised Learning. Topics which will be covered in this unit include Artificial Neural Networks, Vector Quantisation and Clustering, Combinatorial Optimisation, Monte Carlo Methods, Genetic Algorithms, Simulated Annealing, Ant Colony Optimisation, and Fuzzy Logic. Study-unit Aims: The study-unit aims to: - Introduce students to the field of machine learning, search and optimization; - Help students understand different algorithms that can be used to solve typical problems; - Introduce the theoretical foundations of machine learning, and search and optimization problems; - Enable the student to choose the right algorithms and methods to solve problems; - Prepare students for more advanced machine learning topics, expert systems and fuzzy logic; - Prepare students for other study-units, and dissertations that require knowledge of machine learning techniques. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - Analyse and determine how and why stochastic and approximate methods are required to solve certain types of problems; - Demonstrate an understanding of the difference between supervised and unsupervised learning models; - Implement and understand basic machine learning techniques; - Identify problems that can be tackled using these algorithms. 2. Skills: By the end of the study-unit the student will be able to: - Use Machine Learning techniques to solve real-world problems; - Choose the right algorithms to solve problems which may be intractable using other methods or ones that are poorly defined. PART TWO – Introduction to Deep Learning Deep Learning systems, or deep neural networks, are increasingly taking over all AI tasks, ranging from language understanding, speech and image processing to autonomous driving. It is a type of Machine Learning technique that enables computer systems to improve with experience and data, whilst at the same time offering great power and flexibility. The study unit will expose students to the basic concepts of deep learning and their applications in various AI tasks. It will also cover the most established deep learning algorithms and architectures, and analyse the different scenarios they are used in. Study-unit Aims: The study-unit aims to: - Introduce students to deep learning; - Introduce the basic theoretical foundations of deep learning; - Help students understand the different building blocks of a deep learning architecture; - Enable the student to select the most appropriate architecture and/or library/framework to solve a machine learning problem; - Prepare students for other study-units and/or dissertations that require knowledge of deep learning. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - Analyse the different building blocks of a deep learning system; - Demonstrate an understanding of how the building blocks work; - Comprehend the generic components of a deep learning architecture; - Given a machine learning problem, decide what type of deep learning architecture to use to solve that problem. 2. Skills: By the end of the study-unit the student will be able to: - Discuss and critically analyse different deep learning architectures; - Identify scenarios where the different types of techniques are best suited; - Implement their own deep learning system using available libraries and frameworks. Main Text/s and any supplementary readings: Course notes and references given in class. |
||||||||||||
| RULES/CONDITIONS | Before TAKING THIS UNIT YOU ARE ADVISED TO TAKE CSA1017 OR TAKE ICT1018 | ||||||||||||
| STUDY-UNIT TYPE | Lecture, Laboratory Session and Tutorial | ||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||
| LECTURER/S | Kristian Guillaumier (Co-ord.) Konstantinos Makantasis |
||||||||||||
|
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. |
|||||||||||||