Core courses

This course offers a comprehensive introduction to core topics in data, data management, and data engineering. It covers the role of data in AI systems, data modelling, dataset creation, data quality improvement, data visualization, dataset integration, data analysis using mining techniques, data storage and retrieval, data distribution, and the impact of inadequate data on subsequent systems and decision making. 

This course aims to explore and apply essential concepts and assumptions in Machine and Deep Learning. Topics covered include supervised learning, generalization, overfitting, model selection, and specialized architectures such as CNNs, RNNs, and Transformers. The course content includes (un)supervised learning, classification, decision theory, classical statistical learning classifiers, complexity, regularization, support vector classifiers, deep learning as well as the design and analysis of machine learning experiments.

Artificial intelligence and data science tackle complex problems that are difficult to solve through manual programming. Instead, they rely on formal frameworks like logic, graphical models, or Bayesian networks, along with reasoning and optimization techniques, to address such challenges. This course introduces important frameworks for modelling real-world problems and the associated uncertainties. It explores the relationships between these models and methods such as search, inference, learning, and optimization. Topics covered include logical modelling, constraint satisfaction problems, graphical models, Bayesian networks, temporal reasoning, and learning via Markov decision processes and reinforcement learning.

This course focuses on evaluating and ensuring the proper functioning of AI-intensive systems. You will explore the dual challenges of software testing and machine learning-specific evaluation methods. You gain hands-on experience in combining these approaches and learn about cutting-edge advancements. Course topics include testing fundamentals, machine learning evaluation basics, quality assurance at various levels (models, components, systems, cyber-physical systems), adversarial attacks, software testing techniques, and data label validation.

This course aims to foster a responsible mindset, preparing you for ethical and sustainable roles in your future career. You will learn to make informed choices and reflect on Responsible Data Science and AI Engineering, acting with integrity, discuss your duties and roles in your professional career, connect different perspectives, and present your ideas to people with different backgrounds. The course covers social, organizational, professional, and technical aspects of developing DSAIT, considering both systems and human-centric perspectives. Topics include human agency, algorithmic robustness, privacy, data governance, transparency, non-discrimination, fairness, inclusivity, accessibility, and accountability.