Date: Friday February 21st, 2020 11:15 – 12:00
Place: Teknologibygget Auditorium, 2.018, Campus Tromsø
Title: Machine learning for physical simulations
Lecturer: Head of department / Research director of scientific computing Simon Wolfgang Funke, Simula Research Laboratory
This talk explores the intersection between physical simulations and machine learning. Specifically, we will consider simulation models that consist of partial differential equations coupled to machine learning models built using artificial neural networks. This idea is motivated by modern applications in computational science, which are governed by multi-scale and partially unknown physically processes that are too complex or poorly understood to be explicitly represented by the governing equations or numerical methods. At the same time, the plummeting cost of sensors, computational power, and data storage in the last decade offers new opportunities for data-driven modelling of such physical systems. While both physical modelling and purely data-driven methods are active independent research areas, little attention has been paid to the intersection of the two.