Test Projects

tagged posts

this pages acronym: tp

Latest Post

… Mathematics of Machine Learning 2025 …

Recent Posts

… ACAT 2025 …

… 3rd RL4AA Workshop 2025 …

pages

• Title: Page Not Found Teaser: Pname: Url: /404.html excerpt: Page not found. Your pixels are in another canvas. abstract:
• Title: about ... Teaser: Pname: Url: /about.html excerpt: ... artificial intelligence abstract:
• Title: About Teaser: Pname: Url: /about/ excerpt: abstract:
• Title: AI Events Teaser: Pname: Url: /events/accelerator.html excerpt: ... for accelerators abstract:
• Title: Publications Teaser: Pname: Url: /publications/accelerator.html excerpt: ... for accelerators abstract:
• Title: Accelerator Research Teaser: Pname: Url: /science/accelerator.html excerpt: ... and machine learning abstract:
• Title: Team Teaser: Pname: Url: /teams/accelerator.html excerpt: ... for accelerators abstract:
• Title: acclaim Teaser: Pname: Url: /projects/acclaim.html excerpt: Accelerating Science with Artificial Intelligence and Machine Learning abstract: Das ACCLAIM-Projekt wird neuartige, hochmoderne Techniken der künstlichen Intelligenz (KI) sowie des maschinellen Lernens (ML) untersuchen und weiterentwickeln, um einige der dringendsten Herausforderungen im Zeitalter extrem großer Datenmengen in den Bereichen Photonenwissenschaft, Teilchenphysik sowie Beschleunigerforschung anzugehen. KI und ML sind besonders geeignet um (nicht-lineare) Prozesse in multi-dimensionalen Parameterräumen zu steuern und effiziente Performance-Optimierung zu erreichen. Das frühere Innovationspoolprojekt AMALEA hat bereits eindrucksvoll gezeigt, wie sehr Beschleuniger von einem Einsatz innovativer ML und KI Methoden profitieren können. ACCLAIM wird auf diesen Ergebnissen aufbauen, und diesen Erfolg auf die Gebiete der lasergetriebener Plasmabeschleuniger, Anomalieerkennung im Betrieb von Großforschungs-anlagen und der Anwendung von Quanten-Computing erweitern
• Title: Ilya Agapov Teaser: Pname: Url: /people/agapov.html excerpt: abstract:
• Title: amalea Teaser: Pname: Url: /projects/amalea.html excerpt: Accelerating Machine Learning for physics abstract:

  Motivation and Goals of the Project

  • we are seeing an explosion of the amount of data in all accelerator based research fields
  • this is true for all large scale research infrastructures in the research field of Mater:
  • LHC, Belle-2 and future accelerators, EU-XFEL, PETRA-III/IV, BESSY, KARA,....
  • Machine Learning (ML) promises a possible quantum leap in scientific computing and big data analysis
  • enormous compute power through dedicated hardware (GPUs, FPGAs,...)
  • high performance und flexibility in the analysis of complex data

  Goals:

  • systematic evaluation and application of ML methods to Particle Physics, Accelerator research and photon science
  • explore possibilities and limits
  • development of a solid hardware and software infrastructure in the centres
  • exploit synergies for establishing cross disciplinary competences in the application of AI/ML methods in the the physics research
• Title: Publications Teaser: Pname: Url: /publications/astroparticles.html excerpt: ... for astroparticles abstract:
• Title: Autonomous Accelerator Teaser: Pname: Url: /projects/autonomous-accelerator.html excerpt: accelerator physics, control theory and computer science combined. abstract: Modern particle accelerators provide exceptional beams for new discoveries in science. The required flexibility, number of operation modes, and better performance in simultaneously more compact and more energy-efficient accelerators demand advanced control methods. One major challenge is the start-up of such accelerators, which requires frequent manual intervention. Low repetition rates, often only one acceleration event per second, lead to slow optimization rates, thus demanding expert knowledge. Although a complete autonomous accelerator seems far from being reachable, this project takes the first steps by bringing reinforcement learning to accelerator operation. Reinforcement learning yields a policy for every initial state taking the impact of the current action on the future into account, eventually replacing the need for manual intervention.
  
  This project focuses on the longitudinal bunch profile of two accelerators, ARES and FLUTE, located at DESY and KIT, respectively. These two test accelerators are dedicated to research and thus offer the unique opportunity of sufficient beam time to develop such a reinforcement learning algorithm. Furthermore, these similar accelerators allow detailed research about the transferability of such algorithms and the resulting control agents. The interdisciplinary project team in this collaboration, including accelerator physics, control theory and computer scientist, opens new approaches to on the path toward autonomous accelerators.
• Title: Ivo Matteo Baltruschat Teaser: Pname: Url: /people/baltruschat.html excerpt: abstract:
• Title: Lynda Boukela Teaser: Pname: Url: /people/boukela.html excerpt: abstract:
• Title: Annika Eichler Teaser: Pname: Url: /people/eichler.html excerpt: abstract:
• Title: Events Teaser: Pname: Url: /events/ excerpt: ... for AI and related topics abstract:
• Title: Teaser: Pname: Url: /feed.xml excerpt: abstract:
• Title: Frank Gaede Teaser: Pname: Url: /people/gaede.html excerpt: abstract:
• Title: AI Events Teaser: Pname: Url: /events/general.html excerpt: ... general abstract:
• Title: Christian Grech Teaser: Pname: Url: /people/grech.html excerpt: abstract:
• Title: Arne Grünhagen Teaser: Pname: Url: /people/gruenhagen.html excerpt: abstract:
• Title: Helmholtz Analytics Framework Teaser: Pname: Url: /projects/haf.html excerpt: Helmholtz Analytics Framework is a data science pilot project funded by the Helmholtz Initiative and Networking Fund. abstract: The Helmholtz Analytics Framework (HAF) is a data science pilot project funded by the Helmholtz Initiative and Networking Fund. Six Helmholtz centers will pursue a systematic development of domain-specific data analysis techniques in a co-design approach between domain scientists and information experts in order to strengthen the development of the data sciences in the Helmholtz Association. In challenging applications from a variety of scientific fields, data analytics methods will be applied to demonstrate their potential in leading to scientific breakthroughs and new knowledge. In addition, the exchange of methods among the scientific areas will lead to their generalization. The Helmholtz Analytics Framework is complementary to the Helmholtz Data Federation (HDF) in that the developed libraries will be made available there first.
• Title: Philipp Heuser Teaser: Pname: Url: /people/heuser.html excerpt: abstract:
• Title: Helmholtz Imaging Teaser: Pname: Url: /projects/hip.html excerpt: Helmholtz Imaging Service Team at DESY. abstract: Helmholtz Imaging supports scientists from all Helmholtz Centers with tasks related to scientific imaging. HI covers the entire pipeline from data acquisition to data analysis. For this the HI Service Team at DESY offers its expertise in classical image analysis algorithms and its AI expertise.
  For any inquires or questions write to helpdesk@helmholtz-imaging.de or to philipp.heuser@desy.de.
• Title: hir3x Teaser: Pname: Url: /projects/hir3x.html excerpt: Helmholtz International Laboratory on Reliability, Repetition, Results at the most Advanced X-Ray Sources. abstract: The revolutionary new capabilities of X-ray free-electron lasers have launched a new field of ultrafast X-ray science. FELs generate femtosecond-duration X-ray pulses with a peak brightness more than a billion times higher than any previous source. This has led to our first direct measurements of chemistry and catalysis in action at the atomic scale, movies of magnetisation dynamics at the nanoscale, the observation of the evolution of exotic quantum dynamics (such as squeezed phonons) in solids, the generation and study of extreme states of matter as found in the cores of stars and planets, or atoms stripped of electrons from the inside giving new insights into atomic structure. FELs have also provided superior images of proteins that are free from effects of radiation damage that plague the conventional methods of X-ray crystallography and cyro-electron microscopy. The methodologies used in such experiments fundamentally differ from those at conventional sources, similar in some ways to the change in optical spectroscopy brought about by the introduction of optical lasers. Complex measurements are made in single pulses, but the full dataset is often aggregated over many millions of shots, as conditions or settings are scanned or to capture rare transient events. As we transition from proof-of-principle experiments towards work-horse measurements of real systems by non-expert users, we must expand experimental capabilities and reliability to be able to collect enormous datasets at high rates, over long periods of time. Such is the promise created by the specialized facilities FLASH, the European XFEL, and the LCLS II, located in Hamburg and California, which produce pulses at up to megahertz rates. But an experiment only works as well as its least-reliable component, and to profit from this capacity requires optimizing all sub-systems of the source and instrumentation. Only then can we acquire the necessary datasets to explore the full structure and dynamics of complex systems at atomic length and time scales. In this Helmholtz International Laboratory, we aim to address the reliability and throughput of various subsystems to achieve high-rate FEL measurements of complex systems. The Laboratory is organized into four work packages that each propose a novel and bold approach to improve reliability. This starts from applying machine learning to the operation of the accelerator and generation of X-ray pulses, as well as to the detection and analysis of X-ray signals. We aim to deploy robotic control of the delivery of samples to avoid interruptions and downtime, and to address challenges in the transport of high-power X-ray beams to experiments. These issues are common to our high-rate facilities and are best addressed collaboratively with pooled resources. Common solutions will enable standardization of experiments and protocols which will further foster collaboration in other areas and promote reliability and ease of use.
• Title: Teaser: Pname: Url: / excerpt: AI related projects, groups and activities on campus abstract:
• Title: AI Events Teaser: Pname: Url: /events/information-technology.html excerpt: ... for information technology abstract:
• Title: Publications Teaser: Pname: Url: /publications/information-technology.html excerpt: ... for information technology abstract:
• Title: Information Technology Teaser: Pname: Url: /science/information-technology.html excerpt: ... research and applications in AI abstract:
• Title: Team Teaser: Pname: Url: /teams/information-technology.html excerpt: ... for information-technologys abstract:
• Title: Intelligent Process Controls Teaser: Pname: Url: /projects/ipc.html excerpt: Data-driven fault diagnosis, autonomous accelerators and advanced feedbacks. abstract: Intelligent Process Controls (IPC) is a subgroup of the Machine Beam Controls (MSK) group at DESY, pushing forward innovative research into autonomous accelerators using reinforcement learning and other cutting-edge optimization techniques. IPC is also engaged in developing advanced feedbacks and enhancing fault diagnosis and anomaly detection through machine learning. By bringing together an exceptional interdisciplinary team of experts from control theory, computer science and physics, IPC aims to solve some of the most challenging problems facing particle accelerators today and in the future, including increasing their availability and developing autonomous accelerators. With a strong connection to academia and an unwavering commitment to forward developments in this field, IPC remains at the forefront of groundbreaking research and technology advancement.
• Title: Nur Zulaiha Jomhari Teaser: Pname: Url: /people/jomhari.html excerpt: abstract:
• Title: Jan Kaiser Teaser: Pname: Url: /people/kaiser.html excerpt: abstract:
• Title: Sahar Kakavand Teaser: Pname: Url: /people/kakavand.html excerpt: abstract:
• Title: Raimund Kammering Teaser: Pname: Url: /people/kammering.html excerpt: abstract:
• Title: Teaser: Pname: Url: /assets/js/lunr/lunr-en.js excerpt: abstract:
• Title: Teaser: Pname: Url: /assets/js/lunr/lunr-gr.js excerpt: abstract:
• Title: Teaser: Pname: Url: /assets/js/lunr/lunr-store.js excerpt: abstract:
• Title: Teaser: Pname: Url: /css/main.css excerpt: abstract:
• Title: Teaser: Pname: Url: /assets/css/main.css excerpt: abstract:
• Title: Publications Teaser: Pname: Url: /publications/materials.html excerpt: ... for materials abstract:
• Title: Team Teaser: Pname: Url: /teams/materials.html excerpt: ... for materialss abstract:
• Title: mdlma Teaser: Pname: Url: /projects/mdlma.html excerpt: Multi-task Deep Learning for Large-scale Multimodal Biomedical Image Analysis. abstract: MDLMA, acronym for ‘Multi-task Deep Learning for Large-scale Multimodal Biomedical Image Analysis’, is a joint research project of the Helmholtz-Zentrum Hereon, the Deutsche Elektronen-Synchrotron DESY, the University of Lübeck (UzL) and the company Syntellix AG. It is funded by the Federal Ministry of Education and Research (BMBF), grant number 031L0202A. The project is lead and coordinated by Prof. Dr. Regine Willumeit-Römer and Dr. Julian Moosmann. In order to optimise biodegradable Mg-based implants with respect to their mechanical, biological and degradation properties, to understand the mechanisms governing the interactions between microstructure, mechanical properties, biology and degradation, and to tailor implants for specific applications, large amounts of multimodal biomedical image data have to be analyzed. Modalities include laboratory X-ray computed tomography (CT), synchrotron radiation micro-computed tomography (SRμCT), magnetic resonance imaging (MRI), small angle X-ray scattering (SAXS) and histology. Recurrent image analysis tasks considered within this project are registration, segmentation/classification, and image enhancement (e.g. artifact or noise reduction) using deep learning (DL) approaches. Further, we will devise new multi-task DL methods that are able to integrally combine different complementary tasks and transfer knowledge across individual analysis tasks. In order to facilitate the application of these multi-task solutions for other domains, modalities and tasks, a unified framework will be developed that enables a quick and efficient implementation and application of data analysis tasks.
• Title: Events Teaser: Pname: Url: /news/ excerpt: ... for AI and related topics abstract:
• Title: AI Events Teaser: Pname: Url: /events/particles.html excerpt: ... particle physics abstract:
• Title: Publications Teaser: Pname: Url: /publications/particles.html excerpt: ... for particles abstract:
• Title: Particle Physics Teaser: Pname: Url: /science/particles.html excerpt: ... and machine learning abstract:
• Title: Team Teaser: Pname: Url: /teams/particles.html excerpt: ... for particless abstract:
• Title: People Teaser: Pname: Url: /people/ excerpt: ... working in AI and related topics abstract:
• Title: AI Events Teaser: Pname: Url: /events/photon-science.html excerpt: ... for photon science abstract:
• Title: Publications Teaser: Pname: Url: /publications/photon-science.html excerpt: ... for photon-science abstract:
• Title: Team Teaser: Pname: Url: /teams/photon-science.html excerpt: ... for photon-sciences abstract:
• Title: Photon Science Teaser: Pname: Url: /science/photon-science.html excerpt: ... and machine learning abstract:
• Title: PickYOLO Teaser: Pname: Url: /projects/pickyolo.html excerpt: Deep learning particle detector for annotation of cryo electron tomograms abstract: The Marlovits team from CSSB and the Helmholtz Imaging team from DESY IT collaborate on the development of a particle detector for annotation of cryo electron tomograms. For this YOLO, a standard deep learning object detection and localisation architecture is tailored to the specific needs of analysing 3D tomographic data.
• Title: Projects Teaser: Pname: Url: /projects/ excerpt: ... for AI and related topics abstract:
• Title: Machine learning the trilinear and light-quark Yukawa couplings from Higgs pair kinematic shapes Teaser: Pname: Url: /publ-template/ excerpt: abstract:
• Title: Publications Teaser: Pname: Url: /publications/ excerpt: ... for AI and related topics abstract:
• Title: Frank Schluenzen Teaser: Pname: Url: /people/schluenzen.html excerpt: abstract:
• Title: Maximilian Schütte Teaser: Pname: Url: /people/schuette.html excerpt: abstract:
• Title: Science Teaser: Pname: Url: /science/ excerpt: ... and AI pursued abstract:
• Title: Teaser: Pname: Url: /single/ excerpt: abstract:
• Title: SRµCT segmentation Teaser: Pname: Url: /projects/srct.html excerpt: Segmentation of Synchrotron CT data. abstract: We are using various DL architectures for the segmentation of SRµCT data, primarily focussed on data collected at the hereon beamlines at Petra III. Within this project semantic segmentation and instance segmentation is addressed.
• Title: Oliver Stein Teaser: Pname: Url: /people/stein.html excerpt: abstract:
• Title: Teams Teaser: Pname: Url: /teams/ excerpt: ... working with AI and related topics abstract:
• Title: Test Projects Teaser: Pname: tproject Url: /tp/ excerpt: ... related to AI abstract: short description of project over more than 1 line?!
• Title: Sergey Tomin Teaser: Pname: Url: /people/tomin.html excerpt: abstract:
• Title: UniSef Teaser: Pname: Url: /projects/unisef.html excerpt: Universal Segmentation Framework. abstract: UniSef, acronym for ‘Universal Segmentation Framework’, is a joint research project of the Helmholtz-Zentrum Hereon, and the Deutsche Elektronen-Synchrotron DESY. The project is lead and coordinated by Philipp Heuser and Julian Moosmann. Segmentation of the reconstructed tomograms is essential for almost all projects. In particular instance segmentation of 3D volumetric data where objects of the same identity have to be separated and identified is a challenging task. Our aim is to have afully automatic segmentation pipelines generalizable to SRCT data. Within this project deep learning approaches for 2d and 3d instance segmentation is addressed.
• Title: Bianca Veglia Teaser: Pname: Url: /people/veglia.html excerpt: abstract:
• Title: Prof.Dr. Regine Willumeit Teaser: Pname: Url: /people/willumeit.html excerpt: abstract:
• Title: Teaser: Pname: Url: /page2/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page3/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page4/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page5/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page6/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page7/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page8/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page9/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page10/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page11/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page12/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page13/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page14/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page15/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page16/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page17/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page18/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page19/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page20/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /page21/ excerpt: AI related projects, groups and activities on campus abstract:
• Title: Teaser: Pname: Url: /sitemap.xml excerpt: abstract:
• Title: Teaser: Pname: Url: /robots.txt excerpt: abstract:
• Title: Teaser: Pname: Url: /css/main.css.map excerpt: abstract:
• Title: Teaser: Pname: Url: /assets/css/main.css.map excerpt: abstract:

projects

collections

• posts