Course overview
The aim of this course is to deepen students' understanding of advanced concepts in artificial intelligence (AI), focusing on probabilistic reasoning, Bayesian networks, and the use of pre-trained models within AI systems. Building on knowledge about probabilistic concepts and foundational algorithms of AI, students will learn to apply these advanced techniques to solve complex problems and integrate ethical practices in AI applications, ensuring their preparedness for emerging AI challenges and innovations. These skills will enable students to develop complex AI-enabled systems and prepare them for further studies in the discipline.
Course learning outcomes
- Apply probability concepts, axioms, random variables, and distributions in modelling uncertainty and making statistical inferences within given AI contexts
- Apply the Bayesian rule and conduct inference on Probabilistic Graphical Models for decision-making
- Implement probabilistic reasoning over time using models such as Hidden Markov Models and the Viterbi algorithm to solve sequential inference tasks
- Apply pre-trained foundation models to perform tasks in natural language processing and computer vision
- Assess model performance and identify areas for improvement in real-world applications
- Apply principles of fairness, explainability, and causality in AI system development, ensuring that their AI solutions are ethically sound and socially responsible