Project description DEENESFRITPL Machine learning could become a powerful tool in physics research Machine learning, the study of computer algorithms that improve automatically through experience, has proven capable of solving complex engineering problems in image recognition, automated translation and gaming. It is now also being considered for applications in theoretical physics due to its ability to identify patterns in high-dimensional data and efficiently approximate complicated functional relationships. The aim of the EU-funded COMPLEX ML project is to make this relationship between machine learning and physics research stronger. Researchers will use ideas and methods from the physics of disordered systems to boost the performance and training of state-of-the-art machine learning algorithms. Furthermore, machine learning techniques will be combined with modern computational physics methods to develop new tools for disordered systems. Show the project objective Hide the project objective Objective 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. Fields of science natural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learningnatural sciencesphysical sciencestheoretical physicsnatural sciencescomputer and information sciencesartificial intelligencecomputational intelligencehumanitiesphilosophy, ethics and religionphilosophy Keywords Machine learning disordered systems renormalization group (RG) soft materials Programme(s) H2020-EU.1.3. - EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions Main Programme H2020-EU.1.3.2. - Nurturing excellence by means of cross-border and cross-sector mobility Topic(s) MSCA-IF-2019 - Individual Fellowships Call for proposal H2020-MSCA-IF-2019 See other projects for this call Funding Scheme MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF) Coordinator UNIVERSITAT ZURICH Net EU contribution € 260 840,64 Address RAMISTRASSE 71 8006 Zurich Switzerland See on map Region Schweiz/Suisse/Svizzera Zürich Zürich Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Total cost € 260 840,64 Partners (1) Sort alphabetically Sort by Net EU contribution Expand all Collapse all Partner Partner organisations contribute to the implementation of the action, but do not sign the Grant Agreement. THE UNIVERSITY OF CHICAGO United States Net EU contribution € 0,00 Address S ELLIS AVE 5801 ROOM 503 60637 Chicago Illinois See on map Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Total cost € 165 265,92