Universiteit Utrecht (UU) • Master Artificial Intelligence

This document contains notes and summaries covering the content of the course Human-Centered Machine Learning within the Artificial Intelligence Master at Utrecht University. It is divided into two parts: Explainability and Fairness. It covers the following topics: - intro to XAI - interpretable models - model agnostic interpretability methods - neural network interpretability - intro to FAI - measuring fairness - interventions & making fair systems

This document contains notes and summaries covering the content of the course Cognitive Modeling within the Artificial Intelligence Master at Utrecht University. This is the list of topics: - computational rationality - process modeling and neuroscience - machine learning 1: principles and applications - machine learning 2: biologically inspired learning - probabilistic models: compositional cognitive models - probabilistic reasoning: communication and probabilistic models of pragmatics -...

This is a complete summary of all the topics covered in the course "Intelligent Agents" in block 1 of the first year of the Master in Artificial Intelligence at Utrecht University. The topics covered are the following: - Agent architectures - Ontology description logics - Description logics reasoning - Resource description framework and web ontology language - Agents for privacy - Agents for collaborative privacy - Trust in agents and the beta reputation system - Referral systems -...