Name: Machine Learning in Natural Sciences: from Quantum Physics to Nanoscience and Structural Biology
Start: 2022-09-19T09:00:00+02:00
End: 2022-09-22T16:00:00+02:00
Location: CFEL (Building 99)

Machine Learning in Natural Sciences: from Quantum Physics to Nanoscience and Structural Biology

from Monday, September 19, 2022 (9:00 AM) to Thursday, September 22, 2022 (4:00 PM)

Monday, September 19, 2022

9:00 AM Welcome
Welcome
9:00 AM - 9:15 AM
Room: Seminarraum 1-3
9:15 AM
9:15 AM - 10:45 AM
Room: Seminarraum 1-3
Contributions

9:15 AM Turning a physical system into a self-learning machine - Florian Marquardt (MPL Erlangen)

10:00 AM Depth requirement reduction using sequential execution - Adrián Pérez Salinas (Leiden University)

10:15 AM Reducing Barren Plateaus in Quantum Algorithm Protocols - Lukas Broers (Universität Hamburg)

10:30 AM Characterization of Few-femtosecond Near-infrared Pulses using Machine Learning approach - Daria Kolbasova (CFEL DESY, Department of Physics UHH)
10:45 AM Coffee Break
Coffee Break
10:45 AM - 11:15 AM
Room: Seminarraum 1-3
11:15 AM
11:15 AM - 12:45 PM
Room: Seminarraum 1-3
Contributions

11:15 AM Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks - Marin Bukov (Sofia University)

12:00 PM Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks - Friederike Metz (Okinawa Institute of Science and Technology)

12:15 PM Online adaptive estimation of decoherence timescales for a single qubit - Muhammad Junaid Arshad (Heriot-Watt University)

12:30 PM Robust quantum dot charge autotuning with Bayesian Neural Networks - Victor Yon (Institut Interdisciplinaire d’Innovation Technologique (3IT), Laboratoire Nanotechnologies Nanosystèmes (LN2))
12:45 PM Lunch Break
Lunch Break
12:45 PM - 2:45 PM
Room: Seminarraum 1-3
2:45 PM
2:45 PM - 4:00 PM
Room: Seminarraum 1-3
Contributions

2:45 PM Creating community driven challenges to advance Science - Gorka Muñoz-Gil (University of Innsbruck)

3:30 PM Unraveling heterogeneous diffusion in single particle trajectories - Borja Requena (ICFO-The Institute of Photonic Sciences)
4:00 PM Coffee Break
Coffee Break
4:00 PM - 4:30 PM
Room: Seminarraum 1-3
4:30 PM
4:30 PM - 6:00 PM
Room: Seminarraum 1-3
Contributions

4:30 PM Machine Learning for Accelerated Molecular Discovery - Pascal Friederich (Karlsruher Institut für Technologie (KIT))

5:15 PM Robust Image Descriptor for Machine Learning based Data Reduction in Crystallography - Vahid Rahmani (DESY)

5:30 PM PeakNet: Peak Finding for Serial Crystallography - Shah Nawaz (DESY)
6:00 PM
6:00 PM - 9:00 PM
Room: Seminarraum 1-3
Contributions

6:00 PM Machine learning parameters of attosecond pulses based on photoelectron momentum distributions - Tomasz Szoldra (Jagiellonian University in Krakow)

6:00 PM Continuous Machine Learning with generated radio galaxy data - Florian Griese (TU Hamburg)

6:00 PM Classification of quantum phases with quantum machine learning - Teresa Sancho-Lorente ( Instituto de Nanociencia y Materiales de Arag ́on (INMA) and Departamento de F ́ısica de la Materia Condensada)

6:00 PM Building separable approximations for quantum states via neural networks - Antoine Girardin

6:00 PM Object detection on GaN quantum wells SEM images incorporating YOLO network Model - Mahdi Khalili Hezarjaribi (Institut für Angewandte Physik, Technische Universität Braunschweig)

6:00 PM SciFi: An Embedded Asset Store to Organize and Optimize Data Files for Machine Learning - Martin Poppinga (Universität Hamburg)

6:00 PM Estimating the entangling power of a two-qubit gate from measurement data: artificial neural networks versus standard tomography methods - Salwa Shaglel (Universität Siegen)

6:00 PM Adding connections in a restricted Boltzmann machine and testing the Regularized Axons family in deeper architectures - Eloy Piñol Jimenez (ICFO - Institute of Photonic Sciences)

6:00 PM Utilising charge state distributions for calibration of intense XFEL pulses with Bayesian optimisation - Niels Breckwoldt (Universität Hamburg, Center for Free-Electron Laser Science CFEL)

6:00 PM Topological characterization of dynamic chiral magnetic textures using machine learning - Tim Matthies (Universität Hamburg)

6:00 PM Quantum magnetic skyrmions using neural network quantum states - Ashish Joshi (Kyoto University)

6:00 PM Neural quantum states for the simulation of nonequilibrium quantum systems - Damian Hofmann (Max Planck Institute for the Structure and Dynamics of Matter)
Tuesday, September 20, 2022
9:00 AM
9:00 AM - 10:30 AM
Room: Seminarraum 1-3
Contributions

9:00 AM Insights into quantum many-body systems through Hamiltonian reconstruction - Annabelle Bohrdt (Harvard University)

9:45 AM Solving quantum and classical dissipative dynamics with artificial neural networks - Martin Gärttner (Heidelberg University)
10:30 AM Coffee Break
Coffee Break
10:30 AM - 11:00 AM
Room: Seminarraum 1-3
11:00 AM
11:00 AM - 12:30 PM
Room: Seminarraum 1-3
Contributions

11:00 AM Quantum physics data as a playground for machine learning - Evert van Nieuwenburg (Leiden University)

11:45 AM Circuit complexity through phase transitions and its consequences in quantum state preparation - David Zueco (CSIC (Spanish National Research Council))
12:30 PM Lunch Break
Lunch Break
12:30 PM - 3:00 PM
Room: Seminarraum 1-3
3:00 PM
3:00 PM - 4:45 PM
Room: Seminarraum 1-3
Contributions

3:00 PM Physical Parametrisations of Mixed Quantum States with Deep Neural Networks - Filippo Vicentini (EPFL - CQSL)

3:15 PM Machine learning of thermodynamic observables in lattice quantum field theory - Kim Nicoli (Technische Universität Berlin)

3:30 PM Unraveling Quantum Scrambling with Neural Networks - Jan Olle (Max Planck Institute for the Science of Light)

4:00 PM Data-Enhanced Variational Monte Carlo with Neural Network Quantum States - Stefanie Czischek (University of Waterloo)
Wednesday, September 21, 2022
9:00 AM
9:00 AM - 10:30 AM
Room: Seminarraum 1-3
Contributions

9:00 AM AI Usage in Structural Biology - Andrea Thorn (Universität Hamburg)

9:45 AM Chiral Structure Classification by a Convolutional Neural Network - Peer Kasten (Institut für Angewandte Physik, Technische Universität Braunschweig)

10:00 AM Learning Conductance: Gaussian Process Regression for Molecular Electronics - Michael Deffner (Universität Hamburg)
10:30 AM Coffee Break
Coffee Break
10:30 AM - 11:00 AM
Room: Seminarraum 1-3
11:00 AM
11:00 AM - 12:30 PM
Room: Seminarraum 1-3
Contributions

11:00 AM OpenFold: Democratizing access to modeling biomolecules and their interactions - Mohammed AlQuraishi (Columbia University)

11:45 AM Quantum flows neural network for variational solutions of the Schrödinger equation - Andrey Yachmenev (Center for Free-Electron Laser Science, DESY)
12:30 PM Lunch Break
Lunch Break
12:30 PM - 2:30 PM
Room: Seminarraum 1-3
2:30 PM
2:30 PM - 3:30 PM
Room: Seminarraum 1-3
Contributions

2:30 PM What do neural networks learn? On the interplay between data structure and representation learning - Sebastian Goldt (International School of Advanced Studies (SISSA))

3:15 PM Tensor networks and efficient descriptions of classical data - Ivan Kukuljan (Max Planck Institute of Quantum Optics)
3:30 PM Panel Discussion
Panel Discussion
3:30 PM - 4:15 PM
Room: Seminarraum 1-3

4:15 PM Coffee Break
Coffee Break
4:15 PM - 4:30 PM
Room: Seminarraum 1-3
4:30 PM
4:30 PM - 6:00 PM
Room: Seminarraum 1-3
Contributions

4:30 PM Autonomous Materials Research and Discovery at NIST - Aaron Gilad Kusne (NIST)

5:15 PM Deep Learning for Topological Materials - Marcin Płodzień (International Research Centre MagTop, Poland; ICFO – The Institute of Photonic Sciences, Spain)
6:00 PM

6:00 PM - 9:00 PM
Room: Seminarraum 1-3
Thursday, September 22, 2022
9:00 AM
9:00 AM - 10:30 AM
Room: Seminarraum 1-3
Contributions

9:00 AM Towards an Artificial Muse for new Ideas and Understanding in the natural Sciences - Mario Krenn (MPL Erlangen)

9:45 AM Revealing physical concepts learned by artificial neural networks - Sebastian Wetzel (Perimeter Institute)
10:30 AM Coffee Break
Coffee Break
10:30 AM - 11:00 AM
Room: Seminarraum 1-3
11:00 AM
11:00 AM - 12:30 PM
Room: Seminarraum 1-3
Contributions

11:00 AM Machine-learning from heterogenous data: dream or reality? - Claudia Draxl (Humboldt Universität)

11:45 AM Tackling Multimodal Device Distributions in Inverse Photonic Design: Lessons learned from Invertible Neural Networks - Michel Frising (Universidad Autonoma de Madrid)
12:30 PM Lunch Break
Lunch Break
12:30 PM - 2:30 PM
Room: Seminarraum 1-3

Choose timezone