Projektbeschreibung
Neue Algorithmen für maschinelles Lernen von physikalischem Verhalten in Raum und Zeit
Numerische Simulationen werden häufig benötigt, um das Verhalten von Systemen zu untersuchen, deren mathematische Modelle zu komplex sind, um analytische Lösungen zur Verfügung zu stellen. Bei der Untersuchung dieser Phänomene müssen räumliche Dimensionen berücksichtigt werden, die im Hinblick auf die dafür erforderlichen Ressourcen schwer zu berechnen und speichern sind. Im Rahmen des EU-finanzierten Projekts SpaTe sollen neuartige Algorithmen zur Ableitung raum-zeitlicher Funktionen entwickelt werden. Damit wird auch die Erstellung effizienter Darstellungen ermöglicht, von denen Entwickler sagen, dass sie ihre Komplexität und hohe Dimensionalität bändigen werden. Letztendlich wird SpaTe ein besseres Verständnis der physikalischen Welt um uns herum ermöglichen und umfangreiche praktische Anwendungen bieten, die von Apps für soziale Medien bis hin zu selbst fahrenden Autos reichen.
Ziel
Numerical simulations are of tremendous importance for a wide range of scientific disciplines and commercial enterprises. For the majority of these natural phenomena, we not only need to consider the three spatial dimensions, but additionally we need to resolve how these phenomena develop over time. Thus, most natural simulations inherently need to resolve four dimensional functions, and most effects at human scales require fine discretizations along all four axes. As a consequence, these functions require large amounts of resources to compute and store. This problem becomes even more pronounced with the advent of data-driven techniques and machine learning. The learning algorithms effectively add additional dimensions, and the complexity and dimensionality of the corresponding functions explains the current lack of data-driven algorithms for space-time functions despite their enormous potential. Within this research project I plan to address the fundamental difficulties that arise in this setting: I will develop novel algorithms to infer spatio-temporal functions, and to construct efficient representations to tame their complexity and high dimensionality. This project combines numerical simulations with computer vision, and machine learning, and has the potential to radically change the way we work with physical simulations. Not only will it break new ground for fast and controllable VFX animations, but it will additionally facilitate the development of new ways to capture physical effects, in conjunction with algorithms to make physical predictions based on observations. Ultimately, this direction will allow us to better understand the physical world around us. It will help us to analyze sparse and ambiguous measurements such as videos and 3D scans automatically and reliably, with a vast range of practical applications from social-media apps to autonomous vehicles.
Wissenschaftliches Gebiet
Schlüsselbegriffe
Programm/Programme
Thema/Themen
Finanzierungsplan
ERC-COG - Consolidator GrantGastgebende Einrichtung
80333 Muenchen
Deutschland