# Helmholtz AI FFT seminar series #8: </br> Jan Ebert ###### tags: `HelmholtzAI`,`FFT` [ToC] ## :memo: Seminar details **02 December 2021, 11:00 - 12:00** - Speaker: **Jan Ebert**, Helmholtz AI consultant @ Jülich Supercomputing Centre - Title: **JAX is for Joy, Autodiff, and Xeleration** - Chair: **Steve Schmerler** Helmholtz AI consultant @ HZDR - Slides: https://fz-juelich.sciebo.de/s/byGYLFRVyqyG1Zx (short and long version) - blog post: https://www.jan-ebert.com/blog/jax-intro.html (now also includes timing for `jit_looped` in `vmap` section) ### VC details Access to online venue: https://bluejeans.com/456361513/8333 Meeting ID: 456 361 513 Participant code: 8333 Want to dial in from a phone? +49.69.808.84246 (Germany (Frankfurt, German)) +41.43.508.6463 (Switzerland (Zurich, German)) ## :memo: Notes :::info :bulb: Write down notes and/or interesting information of the seminar. For example, observations auxiliar to the content which is not contained in the slidedeck. ::: - autodiff overview: https://github.com/hzdr/autodiff101 ## :question: Questions for the speaker :::info :bulb: Write down any questions or topics you wish to discuss during the seminar _(either with your initials or anonymously)_ ::: > Leave in-line comments! [color=#3b75c6] :arrow_right: ... https://jax.readthedocs.io/en/latest/notebooks/Common_Gotchas_in_JAX.html#control-flow ## :question: Your Feedback :::info :bulb: Write down your feedback about the seminar _(either with your initials or anonymously)_ ::: ### Share something that you learned or liked :+1: - ... ### Share something that you didn’t like or would like us to improve :-1: - (Helene Hoffmann) I would like to either be able to ask questions inbetween, because if I can't understand something right in the beginning I have no chance to follow the rest of the talk. Alternatively, the talk could be provided as a video beforehand so I have the time to find out the things I don't understand myself and have the oppertunity to actually learn something. - (PS) this is an interesting idea. This would be an inverted seminar so to speak. Everybody is expected to watch a prerecorded video and then we focus the time online on a discussion. :::info :pushpin: Want to learn more? ➜ [HackMD Tutorials](https://hackmd.io/c/tutorials) :::
Last changed by  
 
Helmholtz AI
Helmholtz Artificial Intelligence Cooperation Unit. Democratising AI for a data-driven future.
314

Read more

Helmholtz AI FFT seminar series #xx: </br> First speaker, second speaker and third speaker

Tobias HänelPeter Steinbach

1/17/2024
Helmholtz AI FFT seminar series #xx: </br> First speaker, second speaker and third speaker

:memo: Seminar details 07 September 2022, 11:00 - 12:00 Speakers and talk titles: Chandrabali Karmakar (PhD fellow @ DLR)Title: XAI in Earth Observation Ridvan Kuzu (Post-doc, Helmholtz AI consultant @ DLR)Title: Automatic detection of building displacements through LSTM-autoencoder-based feature representations from InSAR data Antony Zappacosta Title: Detecting gamma-ray sources in CTA samples: from traditional image analysis to convolutional neural networks

9/7/2023
Helmholtz AI FFT seminar series #14: </br> Caroline Arnold, Ridvan Kuzu, Kai Konen and Simon Schmitz

[ToC] :memo: Seminar details 3 November 2022, 11:00 - 12:00 Speakers and talk titles: Caroline Arnold and Ridvan Kuzu (AI consultants @ DKRZ and @ DLR): AI4EO Hyperview Challenge Kai Konen and Simon Schmitz (AI consultants @ DLR): Recognition and classification of intracellular filamentous structures

11/3/2022
Helmholtz AI special edition seminar: </br> Martin Voigt

[ToC] :memo: Seminar details 01 February 2022, 10:30 - 11:30 Speaker: Martin Voigt elevait GmbH & Co. KG (elevait.de) Title: Doing Machine Learning Projects in Teams Chair: Peter Steinbach, Head of Helmholtz AI consultant team @ HZDR VC details

2/1/2022
Read more from Helmholtz AI
Published on HackMD