Using Inference for Problems in Complex Systems
Complex systems science aims at explaining the macroscopic behavior of systems composed of many interacting parts that cannot be explained by the independent characteristics of individual components. A critical part of this process is to develop methodologies that allows to obtain information from data. However, very often the approaches we use have hidden assumptions that affect the information we can retrieve from data. In this seminar, I will give a broad overlook of what is Bayesian inference and how we can use it to make our assumptions explicit. Then I will talk about how we can use it to obtain models from our data and to solve problems with complex networks data, by using examples from engineering and neuroscience.
Speaker
-
Marta Sales PardoChemical Engineering Departament, URVMarta Sales-Pardo graduated in Physics at Universitat de Barcelona and obtained a PhD in Physics from Universitat de Barcelona. She then moved to Northwestern University, where she first worked as a postdoctoral fellow and, later, as a Fulbright Scholar. In 2008, she became a Research Assistant Professor at the Northwestern University Clinical and Translational Science Institute with joint appointments in the Department of Chemical and Biological Engineering and the Northwestern Institute on Complex Systems. In 2010 she started the Science and Engineering of Emergent Systems Lab together with Dr. Roger Guimerà at the Dept of Chemical Engineering where she is a Full Professor since 2021. In recognition of her excellence in research she has received the ICREA Academia award twice (2012, 2021). Since 2021 she is a Fellow of the Network Science Society. In 2024 she received and ERC Synergy award and in 2025 she received and Excellence in Research Award from the Serra-Húnter Programme.