Artificial intelligence and machine learning involve the study of algorithms that improve through experience. The fields cover topics that are essential towards obtaining agents with some type of intelligence, including knowledge and learning representations, model learning from data, reasoning and planning under uncertainty, causality, language processing, signals and vision. They often make use of core methods and techniques from optimization, statistics, probability, algorithm design, and so on. This trajectory explores AI and machine learning from multiple perspectives, including principles of AI, theories of representation, AI models, algorithms for learning, reasoning and decision making. There is also an important focus on solutions that are not only accurate but efficient, reliable, interpretative, robust, and trustworthy.
The trajectory contains the following courses:
- 2AMU10 - Foundations of AI,
- 2AMU20 - Generative AI Models,
- 2AMU30 - Uncertainty Representation and Reasoning, and
- 2AMM40 - Advanced Topics In AI
The courses in this trajectory teach you the main techniques and approaches in modern AI. You will learn about the beginnings of AI and machine learning and the developments that led to the current state of the art (2AMU10). You will study theories of uncertainty for robustly representing knowledge and learning from data, and how to use them to support informed and cautious decision making (2AMU30). You will study how to build general purpose models to capture the nature of data and discover patterns in it, as well as to generate new data (2AMU10, 2AMU20). You will understand to which extent models are interpretable and transparent, and you will study methodological foundations and state-of-the-art approaches for explainable machine learning and data analysis (2AMM40, 2AMU30).
For an overview of the full course list of this master program, visit this page.