Model-based Machine Learning (42186)
Model-based Machine Learning leverages the powerful framework of Probabilistic Graphical Models (PGMs) and recent developments in probabilistic programming to allow the combination of domain knowledge with data driven methods in a very simple way.
Data Science for Mobility (42184)
This course introduces the portfolio of tasks and techniques necessary for applying Data Sciences to mobility problems. It includes an introduction to Python programming, data wrangling, problem formulation, Spatial statistics, and the basic suite of machine learning and spatial data processing algorithms.
Agent-based modelling and simulation (42188)
In this course we look at this interaction between agents and focus on the development of agent-based models to describe and simulate the movements of agents in different contexts. This is relevant when monitoring indicators for the environment such as air quality and emissions, monitoring consumption of electricity and water, and describing demand for transport and parking.
Transport System Analysis: Performance and Operations(42187)
Understanding how a transport system operates is at the core of this course. Students will gain knowledge on the key mathematical methods used in the representation of people’s and vehicle’s movement, the network and service performance and key strategies for control and improved efficiency of mobility systems. This course combines key methodological knowledge gains with examples applications from different dimensions of the mobility paradigm.