Machine Learning Applications Engineering
This theme delves into the intricate realm of machine learning algorithms, techniques, and applications with a focus on engineering robust and scalable solutions. The central thread running through this theme is the fusion of theoretical understanding of ML with practical implementation ML-enabled software systems. It explores the art of designing, developing, and deploying machine learning models in a real-world context.
Year 1 |
|||
Quarter 1 |
Quarter 2 |
Quarter 3 |
Quarter 4 |
Software Architecture | Core course | Responsible Computer Science | Research course |
Core course | Theme 1 | Theme 1 | Theme 1 |
Core course | Theme 2 | Theme 2 | Theme 2 |
Credits: each course in a theme is 5EC, so each theme is 15EC.
Students choose 2 themes, each of which has 3 courses in the 2nd, 3rd and 4th quarters of the 1st year. For this theme, you will take the following courses:
Q2 - Elements of Statistical Learning
This course covers all the basic concepts of Statistical Learning, focusing on the classical techniques of Machine Learning before the era of Deep Learning. These concepts include classification, (ridge) regression, (hierarchical) clustering, feature reduction and extraction, model selection and bootstrapping, fairness in Machine Learning. The emphasis is on the concepts rather than mathematical details.
Q3 - Conversational Agents
This course covers different verbal and nonverbal behavioural characteristics of conversation and embodied interaction, such as, intonation, gaze and gestures that humans show when communicating with both other people and machines. This behaviour is then related to different multimodal dialogue functions, including turn-taking, addressing others, and backchanneling, that give shape to the communication process. Topics on interaction with embodied agents and how to design memory models for conversational interaction are also discussed. You will apply this knowledge through the design, development, and evaluation of an embodied conversational agent application that uses a memory model to interact.
Q4 - Release Engineering for Machine Learning Applications
In this course you will learn how to systematically release your applications and make them scalable in an orchestrated environment and how to make your proof-of-concept applications production ready. This course takes you on a journey that starts with continuous integration and then moves on to continuous delivery, continuous deployment, and continuous experimentation. We will discuss the theory and the current research on various related subjects like containerization, testing, or monitoring and you will put the learned theory into practice. As a running example, you will build a pipeline for a machine learning application, which compared to traditional release engineering- poses additional challenges, like data versioning or model deployment.