Inria Chile Talks - “Modeling physical systems with neural networks”

Physics and machine learning share the goal of creating models to predict the behavior of systems based on observations. In recent years, various approaches have emerged that combine both methods under the term physics-informed neural networks, proposing neural network architectures and optimization algorithms that incorporate information about the physics of systems. This presentation will introduce the fundamentals of PINNs, as well as different applications and use cases in the fields of physical chemistry and energy.

Juan Gómez Romero is a professor in the Department of Computer Science and Artificial Intelligence at the University of Granada. His research focuses on the application of Artificial Intelligence and Machine Learning in various areas, such as energy efficiency and misinformation characterization. He is currently the co-director of the SAIL-UGR laboratory and the UGR research team in the IA4TES project (Artificial Intelligence for Sustainable Energy Transition). Previously, he was a professor at Carlos III University of Madrid and a visiting researcher at the Data Science Institute of Imperial College London.