Jan Kieseler
@JanKieseler
Followers
22
Following
33
Media
3
Statuses
21
Joined January 2022
RT @GregorKasieczka: Full paper at Fun work with @DASHHPhD @quunihh student Sebastian and @JanKieseler & Mathias….
arxiv.org
In recent years, neural network-based classification has been used to improve data analysis at collider experiments. While this strategy proves to be hugely successful, the underlying models are...
0
1
0
RT @agbuckley: Nice to sneak this out just before Christmas: solid and actionable advice on designing and implementing LHC — and beyond — M….
arxiv.org
With the increasing usage of machine-learning in high-energy physics analyses, the publication of the trained models in a reusable form has become a crucial question for analysis preservation and...
0
1
0
Are you looking for a postdoc in HEP and also want to push the boundaries of AI in a dynamic new group? Then check out this posting:
0
9
18
RT @CERNCourier: Showcasing the first measurement, by @CMSexperiment, of the top-quark pair production cross section at a centre-of-mass en….
cerncourier.com
The first LHC Run 3 result was among the highlights of the TOP 22 conference, held from 4 to 9 September.
0
3
0
First single-shot reconstruction of about 1000 particles at once in 200 PU in a high granularity calorimeter using machine learning, featuring GravNet and Object Condensation. Great work from @ShahRukhQasim and the whole team!.
0
2
6
RT @dorigo: Congratulations to @JanKieseler, @pietrovischia, @Giles_C_Strong and others for the article "Intelligent Design for Particle D….
ep-news.web.cern.ch
0
5
0
RT @dorigo: A first concrete proof of end to end optimization of experiments!! Forward with @MODECollaborat1 !!.
0
1
0
RT @pietrovischia: Thrilled to announce that our white paper on End-to-End Optimization of Particle Physics Instruments with Differentiable….
arxiv.org
The full optimization of the design and operation of instruments whose functioning relies on the interaction of radiation with matter is a super-human task, given the large dimensionality of the...
0
10
0
RT @amaragraps: I think that this is the first time a physics demo had me laughing in tears.
0
177
0
RT @dorigo: Deep learning 66M parameters with a SGD-optimized nearest neighbor gets you to the same performance of NNs and BDTs! The power….
0
2
0
Setting a trap for long lived and yet undiscovered particles.
journals.aps.org
We propose a two-stage strategy to search for new long-lived particles that could be produced at the CERN LHC, become trapped in detector material, and decay later. In the first stage, metal rods are...
0
0
3
Will AI design our future detectors for us? One small step out of many steps towards AI helping us with design decisions is described in this paper, where we show how it can be used to easily compare different design options for measuring particle energies.
link.springer.com
The European Physical Journal C - We investigate the effect of longitudinal and transverse calorimeter segmentation on event-by-event software compensation for hadronic showers. To factorize out...
0
1
2
RT @TensorFlow: 🧪️ Engineers at the CERN LHC use TensorFlow to reconstruct thousands of particles in one go. Learn how in this guest arti….
blog.tensorflow.org
Learn how engineers at the CERN LHC use TensorFlow to reconstruct thousands of particles in one go in this guest article by Jan Kieseler.
0
55
0
. The power of AI: even tiny energy deposits of particles that otherwise fly through the detector can still be enough to determine their energies.
0
1
2