5 ECTS credits
125 h study time
Offer 1 with catalog number 4021320ENR for all students in the 2nd semester at a (E) Master - advanced level.
The aim of the course is to cover in-depth the latest topics in data science and engineering and to present its applications in the field of big data analytics. As such, the course covers on the one hand the basic and modern principles and trends in machine learning and on the other hand the latest advances in big data systems. The course content is divided in four parts. Part I serves as an introduction to the basics of modern data analytics, including a compact recap on optimisation methods, and provides an introduction to big data systems and the cloud. Part II covers concepts related to multivariate linear and non-linear regression as well as classification problems including logistic regression, softmax. Part III focuses on unsupervised learning, addressing topics related to sparse coding, dictionary learning and clustering. Part IV revolves around MapReduce for big data processing. Part V focuses on neural networks with emphasis on deep convolutional neural networks for images.
The goal of this course is to introduce the fundamental concepts, methods, and technologies relevant for the design of data analytics methods with emphasis on the latest big data analytics applications. The students will have the opportunity to follow a set of lectures, to implement the concepts during lab sessions in Python, and to practically use these concepts in the form of a project. In addition, the students have the opportunity to prepare and deliver a presentation exposing modern concepts in machine learning, thereby adhering to a flipped classroom blended learning paradigm.
At the end of this course, the student will have developed a deep knowledge and understanding in state-of-the-art concepts and technologies in machine learning and big data analytics. The student will understand the basic coding technologies in data analytics systems – including Python libraries, tensorflow, PyTorch, etc. – and will be able to practice these tools in the form of practical sessions. The student will be able to investigate how the acquired theoretical and practical knowledge can be applied to address a practical data analytics problem in the form of a project. The students have also the opportunity to prepare and deliver a presentation on modern concepts in machine learning.
The final grade is composed based on the following categories:
Other determines 100% of the final mark.
Within the Other category, the following assignments need to be completed:
The final exam will be a written evaluation, where the students will address theoretical questions, will be asked to define optimisation functions and problems, as well as to write algorithms that solve specific problems related to machine learning and big data processing. The project will examine the students’ involvement in the seminar sessions, evaluate their in-depth understanding, and assess their practical skills in real-life data analytics tasks. The presentation examines the capability of the students to comprehend, summarize and deliver information related to modern machine learning concepts.
The final grade is composed based on the following examinations: (1) the result of the final written exam, which determines 60% of the final mark; (2) the result of the presentation, which determines 10% of the final mark, (3) the result of a project work, which determines 30% of the final mark.
Use of Generative AI: In the practical sessions and the project, it is prohibited to use generative AI for code generation.
In the project report, it is permitted to use generative AI only as a paraphrasing tool. Any use of generative AI should be properly referenced.
To reference generative AI use, write an acknowledgment of generative artificial intelligence, the specific tool used, and its scope; moreover, attach descriptions of how the information was generated (including the prompts used) and how it was added to your report.
This offer is part of the following study plans:
Master of Electronics and Information Technology Engineering: Standaard traject (only offered in Dutch)
Master of Photonics Engineering: On campus traject
Master of Photonics Engineering: Online/Digital traject
Master of Electrical Engineering: Standaard traject BRUFACE J