Projektbeschreibung
Wie maschinelles Lernen zum Superwerkzeug der physikalischen Forschung wird
Maschinelles Lernen bedeutet, dass künstliche Systeme, etwa Computeralgorithmen, durch Erfahrung Wissen generieren und sich automatisch verbessern. Damit können nachweislich komplexe technische Probleme bei der Bilderkennung, der automatisierten Übersetzung und im Bereich der Spiele gelöst werden. Da durch maschinelles Lernen Muster in hochdimensionalen Daten erkennbar und komplizierte funktionale Zusammenhänge auf wirkungsvolle Weise annäherbar sind, werden nun auch Anwendungen in der theoretischen Physik in Erwägung gezogen. Ziel des EU-finanzierten Projekts COMPLEX ML ist, diese Beziehung zwischen maschinellem Lernen und physikalischer Forschung zu vertiefen. Das Forschungsteam wird anhand von Ideen und Methoden aus der Physik der ungeordneten Systeme die Leistungsfähigkeit und das Training modernster Algorithmen des maschinellen Lernens verbessern. Zudem werden Verfahren des maschinellen Lernens mit modernen Methoden der computergestützten Physik kombiniert, um neue Instrumente für ungeordnete Systeme zu entwickeln.
Ziel
Machine learning (ML) has proven capable of tackling difficult engineering problems in image recognition and automated translation, but even more impressively in domains where traditional algorithmic approaches had struggled, such as game playing. Though the relations between ML and physics are decades old, it only recently attracted a widespread attention of scientists in many subfields of theoretical physics due to its ability to identify patterns in high-dimensional data, and to efficiently approximate complicated functional relationships. At the same time, the empirically oriented philosophy of ML is very different from that of fundamental sciences: a trained model often offers little insights into the qualitatively important aspects of the problem, how the solution was arrived at, what are the guarantees of correctness, and, crucially, how to generalize it. Bridging this conceptual gap is thus of fundamental importance, if ML is to become a powerful and controlled tool in physics research. This interdisciplinary projects aims to bring about successful development and application of ML methods resulting in qualitatively new insights in physics by following a twofold strategy. On the one hand, the performance and training of state-of-the-art ML algorithms will be improved using methods of complex and disordered systems. Specific problems targeted will include novel reinforcement learning schemes, and training of binary neural networks, with input from industrial R&D researchers. On the other, cutting edge ML techniques, particularly those with a strong underpinning in information theory, will be combined with modern computational physics methods to develop new tools for disordered systems. This is motivated by the possibility of using them to study soft materials, providing better understanding of these ubiquitous but complex systems.
Wissenschaftliches Gebiet
- natural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learning
- natural sciencesphysical sciencestheoretical physics
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
- humanitiesphilosophy, ethics and religionphilosophy
Schlüsselbegriffe
Programm/Programme
Thema/Themen
Aufforderung zur Vorschlagseinreichung
Andere Projekte für diesen Aufruf anzeigenFinanzierungsplan
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Koordinator
8006 Zurich
Schweiz