#hepml search results

.@brucedenby is the author of the very first paper on AI and Particle Physics back in 1988, when he was a post-doc in Orsay ( @IJCLab @cnrs_in2p3) working in the @CERN LEP DELPHI experiment. He was almost fired for this! #HEPML @dorigo @KyleCranmer @GregorKasieczka

Tagging the #hepml community : @KyleCranmer @ClaudiusKrause @DanielWhiteson @SergeiGleyzer @BPNachman @Stefanog @HEPfeickert @glouppe @Giles_C_Strong @DaniloJRezende @SaltyBurger @vlimant @lukasheinrich_ @michaelkagan @dorigo @pietrovischia

Also featuring the #CaloChallenge! (Yes, the write-up will come later this year!) #EuCAIFCon24 #HEPML

I wonder if that includes our papers from #HighEnergyPhysics? 🤔🤔🤔 ...anyway, on it! #HEPML

Just registered for EuCAIFCon 2024! aanmelder.nl/eucaifcon24 #HEPML #AI4Science

Pre Christmas #HEPML papers, part 3 Together with Ben Nachman (@BPNachman), Ian Pang, David Shih, and Yunhao Zhu, we wondered: When you learn to simulate #CalorimeterShowers with #NormalizingFlows, what else can you do with the likelihood of showers that you now have access to?

Pre Christmas #HEPML papers, part 2. Together with Florian Ernst, Luigi Favaro, Tilman Plehn, and David Shih, we investigate how we can go beyond CaloFlow and scale #NormalizingFlows up to high-dimensional #Calorimeter data, while still being really fast in generation. 1/5

Wonderful timing, thanks for sharing! #CaloChallenge #HEPML

... with experience from #higgsml and #trackml competitions ! #hepml

With a special Far-Universe hackathon to prototype a hopefully #neurips 2024 competition. A #higgsml competition on steroids, where participant need to handle uncertainties on the inputs and output: the expected answer is a confidence interval ! #hepml

This was quite an adventure to set up but thrilled it eventually worked out. I anticipate several AI and Fundamental Physics PhD topics to be proposed under the theme #AI and uncertainties of @UnivParisSaclay COFUND DeMythif.AI #HEPML dataia.eu/actualites/acc…

Hey #HEPML community, the #LivingReview just got a facelift. It now has expandable sections, a table of contents, a separate list of recent additions, a search bar, ... Check it out: iml-wg.github.io/HEPML-LivingRe…

Happy to share that I'm one of the new managers of the #HEPML #LivingReview.

Finally happening ! 35 years later, @brucedenby is back at LAL (now @IJCLab) Orsay. Telling us how he came up with the very first AI in HEP paper. #hepml

This is exactly the reason why we’ve always used CMS Open data in the end-to-end project for all our studies (tagging, etc) because data quality and fidelity matters. Thanks for this nice study and for sharing the dataset #hepopendata #hepml

After 2 years delay, thrilled to see this event finally happening hybrid at @PascalInstitut ! AI and physics, with 3 successive workshops on Representation learning, Uncertainties, and Generators, and a final general conference. #hepml indico.ijclab.in2p3.fr/event/5999/tim…

Yep, I’ll try and connect what we do with AI with what AI does elsewhere, and what are the specific challenges for us….#hepml

Will deal both about ML for physics and physics for ML. Amazing plenary speakers. Plus contributed posters and short talks, deadline 27th August. #hepml

That’s quite a high bar, I’ll definitely have a look....#hepml @Giles_C_Strong did you see that ?

... and it’s out! We finally manage to release the final « Throughput » paper on #trackml challenge. Check it out to see how participants achieved one order of magnitude speed up through amazing tricks. arxiv.org/abs/2105.01160 #hepml

Wonderful keynote talk by Johann Brehmer at #ACAT2019, strongly recommend checking his slides and papers indico.cern.ch/event/708041/c… Several talks on mentioning LFI in this conference, so glad to see #HEPML focus increasingly shifting towards inference tasks from s/b classification

@INSIGHTS_EU CERN ESR @sitong_an presenting progress on end-to-end learning for jets at the INSIGHTS_EU midterm review meeting #hepml #lhc

Here are my slides from the 2nd IML workshop on how #HEPML problems are not supervised classification, why that matters when simulations are imperfect and a possible way around it via systematics-aware losses pdecastr.web.cern.ch/pdecastr/iml_w…

Release of #trackml challenge on @kaggle imminent ! Name of the game is to connect the points measured by a @cern experiment. Stay tuned... #HEPML

At #SC19 in Denver, say hello if you are around #HEPML

The first @IN2P3_CNRS #HEPML workshop. indico.in2p3.fr/event/17295/ti…

If you are interested in fast machine learning and its applications in high-energy physics #hepml come to our exhibition booth at #SC19 tomorrow

#AI for High-Energy Physics #HEPML #energy

Over the last few months @LHCbExperiment I've been working on the investigation of ML methods to be used in the Upgrade Trigger, which will require new processing methods to reduce data rates without biasing the filtered samples. #HEPML 1/10

I'll be taking about our recent work in ~1 hour "Learning the likelihood function: moving from classification to inference" indico.cern.ch/event/737584/ #HEPML

Congrats to Vicens Gaitan @ControlByte snatching leadership from Zidmie (65.5% against 64.9%) in our #trackml @kaggle competition. Mickey still third with 64.1%. 3 more above 60%. Good to see 24 more above 50%. #hepml .

And we are off - the 3rd CMS Experiment ML workshop #hepml Many nice ML results that will be public soon

Fun times visiting the @CMSExperiment with @wellingmax and Naftali Tishby. Always impressive. #HEPML

@AnaderiRu visiting RAL to talk about data science for scientists (not just particle physicists) Slides will be available after the lecture #HEPML

1/ Dear #HEPML Twitter. Benchmarking HistFactory on CPU/GPU/TPUs on @GoogleColab and baffled by the results. a) why are (single-core) TPUs slower than GPUs, is the speed-up really only due to data-sharding across cores? b) why do TPU show this zig-zag behavior? due to bfloat16?

Also featuring the #CaloChallenge! (Yes, the write-up will come later this year!) #EuCAIFCon24 #HEPML

.@ferpsihas is spreading the good word about #HEPML to El Congreso Ingeniería Física 2017 at @IBERO_mx.

Part of the #trackML team under the cherry blossoms of @UW U Washington at Seattle, during @ctdwit #ctd2018 workshop. @dhpmrou @SaltyBurger @SteveAFarrell #hepml

Pre Christmas #HEPML papers, part 3 Together with Ben Nachman (@BPNachman), Ian Pang, David Shih, and Yunhao Zhu, we wondered: When you learn to simulate #CalorimeterShowers with #NormalizingFlows, what else can you do with the likelihood of showers that you now have access to?

On Thursday Aug 30 I'll be giving a talk at the @CERN Machine Learning forum about our recent work "Learning the likelihood function: moving from classification to inference" #HepML arxiv.org/abs/arXiv:1805… arxiv.org/abs/arXiv:1805… arxiv.org/abs/arXiv:1808… indico.cern.ch/event/737584/