Register event
3 events found

Keywords: Graph Neural Networks  or Autoencoder  or Model Diffusion  or dataset  or GPU 

  • Deep Learning School

    21 - 24 May 2024

    Filderstadt, Germany

    Deep Learning School https://pan-training.eu/events/deep-learning-school-46deca27-6b8d-4b37-bbe7-5c5e63ad2197 The Active Training Course "Advanced Deep Learning" is hosted over 4 days at (location tba) by the community organization DIG-UM with support from the BMBF-funded ErUM-Data-Hub. The event serves the professional education of young scientists belonging to the ErUM Community. The intensive course on Graph Neural Networks, Transformers, Normalizing Flows and Autoencoders will be held from 21.05.24 - 24.05.24. The course includes a challenge to be worked out and presented by participant subgroups. The workshop is aimed at deep-learning enthusiasts from all ErUM communities (Research on Universe and Matter) who have prior knowledge of neural networks and applied basic concepts of deep learning. A fee of 300€ will be charged for participation in the course. The workshop fee includes the cost of the workshop, accommodation and catering. Registration closes tba. 2024-05-21 17:00:00 UTC 2024-05-24 14:00:00 UTC ErUM-Data-Hub (BMBF) Bernhäuser Forst, Filderstadt, Germany Bernhäuser Forst Filderstadt Germany 70794 [] [] [] workshops_and_courses [] Graph Neural NetworksAutoencoderModel DiffusionNormalizing Flows
  • Fundamentals of Scientific Metadata: Why Context Matters

    18 - 19 June 2024

    Fundamentals of Scientific Metadata: Why Context Matters https://pan-training.eu/events/fundamentals-of-scientific-metadata-why-context-matters This course is an entry-level introduction to the fundamentals of scientific metadata for PhD students, early-career researchers, and postdocs. In this course we will look at the intricate relationship between (digital) research data, metadata, and knowledge; discuss why metadata is critical in today’s research; and explain some of the technologies and concepts related to structured machine-readable metadata. Have you ever struggled to make sense of scientific data provided by a collaborator? Or, even worse, to understand your own data five months after publication... Do you have difficulties in meeting the data description requirements of your funding agency? Do you want your data to have lasting value; but don’t know how to ensure that? Precise and structured descriptions of research data are key for scientific exchange and progress - and for ensuring recognition of your effort in data collection. The solution: make your data findable, accessible, interoperable, and reusable - by describing them with metadata. This course is targeted especially at scientific staff and researchers in the Helmholtz Research Field Matter but is open to anyone who would like to better understand research data annotation with metadata. *What You Will Learn*: * Understanding the vital differences between data and metadata. * Techniques for annotating research data using structured metadata. * Identifying and implementing appropriate metadata frameworks and data repositories. * Developing basic skills in Markdown, JSON, XML. * Exploring tools to improve your metadata annotation capabilities. * Recognizing the role of structured metadata in enhancing your scientific visibility. In this course, we will specifically focus on matter-related datasets, formats, and metadata schemas. However, it is open to anyone interested in learning about structured metadata and its importance in scientific research. 2024-06-18 09:00:00 UTC 2024-06-19 12:30:00 UTC [] [] [] workshops_and_courses [] metadatadata managementdata repositorymatterdataset
  • Fast and Efficient Python Computing School

    24 - 27 September 2024

    Fast and Efficient Python Computing School https://pan-training.eu/events/fast-and-efficient-python-computing-school This is a School organized by the ErUM-Data-Hub with support from DIG-UM. In this school you will learn how Python code can be accelerated. A focus will be placed on numeric NumPy-like array computations. In addition, running these array computations on hardware accelerators, i.e., GPUs, will play a key role in this school. The school is intended for young researchers - especially for PhD students - who regularly work with the scientific Python ecosystem. Requirements are good knowledge of the scientific Python ecosystem, basics of the C++ programming language are beneficial. The school (see timetable) is split into five parts of which three are keynote lectures with hands-on tutorials. The other two comprise an opening talk and a coding group challenge for the participants. A fee of 300€ will be charged for participation in the workshop. ## Topics: * Setting the scene: benefits and disadvantages of the Python programming language and a brief outline how Python programs can be accelerated in general. * Efficient Python Programming: general approaches to accelerate Python code, using C++ in Python and accelerating array computations. * Accelerator Optimised Programming: how array computations can be run on GPUs with typical Deep Learning libraries, such as JAX or TensorFlow. * GPU Programming: understanding the hardware layout, i.e., thread and memory layout and hierarchy and basics of the CUDA toolkit. A focus is set on how to program custom GPU kernels for, e.g., Deep Learning applications (in JAX or TensorFlow). * Group Challenge 2024-09-24 09:30:00 UTC 2024-09-27 18:00:00 UTC [] [] [] workshops_and_courses [] PythonGPUAccelerator Optimised Programming

Note, this map only displays events that have geolocation information in our catalogue.
For the complete list of events in our catalogue, click the grid tab.