qml
qml copied to clipboard
PennyLaneAI
tutorial eqnn force field
Title: Symmetry-invariant quantum machine learning force fields Summary: Tutorial on equivariant QML for learning energy and forces in a H2O molecule Relevant references: https://arxiv.org/abs/2311.11362 Possible Drawbacks: long to train ~10 min
Related GitHub Issues:
If you are writing a demonstration, please answer these questions to facilitate the marketing process.
-
GOALS — Why are we working on this now? implementation of a recent paper
-
AUDIENCE — Who is this for? Chemistry and QML researchers
-
KEYWORDS — What words should be included in the marketing post? Geometric quantum machine learning, force field
-
Which of the following types of documentation is most similar to your file? Demos
Thank you for opening this pull request.
You can find the built site at this link.
Deployment Info:
- Pull Request ID:
1015 - Deployment SHA:
3b1e8bd82664e91fabaeb2340103991fd900f35d(TheDeployment SHArefers to the latest commit hash the docs were built from)
Note: It may take several minutes for updates to this pull request to be reflected on the deployed site.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
Good to see it is deploying! 😄 You can check here the demo PR on the website: https://qml-build-previews.pennylane.ai/pull_request_build_preview/1015/qml/demos/tutorial_eqnn_force_field/
As soon as you think it's ready to review we'll get to it 💪
I think we can get to the reviews. There is a minor problem with the second image I don't know how to fix. But apart from that, it looks in good shape. Thank you! :)
I think we can get to the reviews. There is a minor problem with the second image I don't know how to fix. But apart from that, it looks in good shape. Thank you! :)
Great, Thanks Oriel 💪 @alvaro-at-xanadu will take a first look at it :)
Good morning @alvaro-at-xanadu and @KetpuntoG !
We thank you for your feedback. We revised our demos and have now pushed a revised version. I think it is ready for a second round of reviews. The only thing i can t figure out is how to remove the blue banner behind figure 2 (not that big of a deal though) Thank you
Just to say that we did not forget to take a look to this demo 💪 With QHack we have a little less capacity but we will get to it soon!
Hi! Thanks a lot for your feedback @CatalinaAlbornoz. I have just committed to all the language changes you requested. I have also precised that in the paper better performances are obtained with a deeper model. Also, I have better explained the part with the swapping on line 245 as "This is fulfilled by coupling only the qubits with are neighbors with respect to the 1-2-3-4-1 ring topology, leading to the following operation".
I believe we are now ready to proceed further @KetpuntoG @alvaro-at-xanadu :)
Thank you so much @orielkiss ! 🚀 I'll talk to the designer to create a Thumbnail and marketing to set a publication date. I estimate it will be within approximately 3-4 weeks. As soon as I have news I'll tell you :)
Hey ! for the publication it is possible that marketing may want to include your username in the post. Could you share with me your @username from Twitter (optional)?
Hi @KetpuntoG ! Thank you for the great work, i really feel our demo improved a lot from the first version. Sure you can use my twitter name @oriel_kiss for marketing (and i think Isabel does not have twitter)
Thanks to you for the good work! Tomorrow it will appear on the website but we will officially announce it next week. I will tell you the exact date as soon as marketing confirm me
Awesome! i just remarked something weird happened at training time that never happened with the preview: it seems the training was stopped and then started again with random parameters. is the process different from the preview and the official website? (not a big deal otherwise)
@orielkiss Hey Oriel,
We have to push the Marketing on this one slightly. I will get back to you with a new date shortly, thanks for your patience!
