HomeNews & EventsEuroTechTalk #5: Efficiently learning across open datasets: Cases from the transport domain

EuroTechTalk #5: Efficiently learning across open datasets: Cases from the transport domain

Joint scientific online lecture by Prof. Francisco C. Pereira (DTU) and Prof. Constantinos Antoniou (TUM).

Efficiently learning across open datasets has become increasingly important in the field of machine learning, and has important implications in the Transport field. Transfer learning and meta-learning are two popular techniques that allow models to leverage knowledge gained from one task and apply it to another. Transfer learning focuses on using pre-trained models as a starting point for new tasks, while meta-learning focuses on learning how to learn from as few examples as possible.

In this talk, Professors Pereira and Antoniou will introduce both concepts in the context of Transport research. First, they will discuss transfer learning for traffic state estimation using scalable and non-scalable data from large European cities, and then they will introduce meta-learning for automated fleet rebalancing in Autonomous Mobility on Demand (AMoD) using taxi data from multiple cities.

Practical information

Date and time: Tuesday, 18 April 2023, 13:00-14:00 CET (14-15 IDT)
Location: online
Registration: Is required; please fill in this registration form.


This event is open to all.

Further information

For further information, please contact Anita Schneider (contact details below).

The EuroTechTalks are a series of scientific online lectures by renowned researchers of EuroTech Universities. In the Alliance, we tackle global challenges together. This series highlights some of our scientific collaborations. Find an overview of the series here.


Anita Schneider, EuroTech

Anita Schneider

Communications Manager, EuroTech Brussels Office