Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Manuel Haussmann"'
Autor:
Samu Kurki, Viivi Halla-aho, Manuel Haussmann, Harri Lähdesmäki, Jussi V. Leinonen, Miika Koskinen
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract A growing body of research is focusing on real-world data (RWD) to supplement or replace randomized controlled trials (RCTs). However, due to the disparities in data generation mechanisms, differences are likely and necessitate scrutiny to v
Externí odkaz:
https://doaj.org/article/c146a74003d74704a63de1ec16b0a5df
Publikováno v:
SciPost Physics, Vol 13, Iss 1, p 003 (2022)
Following the growing success of generative neural networks in LHC simulations, the crucial question is how to control the networks and assign uncertainties to their event output. We show how Bayesian normalizing flow or invertible networks captur
Externí odkaz:
https://doaj.org/article/988c444774ff4c0fb30439f510d64f60
Autor:
Sven Bollweg, Manuel Haussmann, Gregor Kasieczka, Michel Luchmann, Tilman Plehn, Jennifer Thompson
Publikováno v:
SciPost Physics, Vol 8, Iss 1, p 006 (2020)
Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers. We sh
Externí odkaz:
https://doaj.org/article/ec6210b12d8546ecb84f625917d92a5e
Publikováno v:
University of Southern Denmark
A probabilistic classifier with reliable predictive uncertainties i) fits successfully to the target domain data, ii) provides calibrated class probabilities in difficult regions of the target domain (e.g.\ class overlap), and iii) accurately identif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::61c341bbc417e32215491b33fc4b8c4b
http://arxiv.org/abs/2106.01216
http://arxiv.org/abs/2106.01216
Following the growing success of generative neural networks in LHC simulations, the crucial question is how to control the networks and assign uncertainties to their event output. We show how Bayesian normalizing flow or invertible networks capture u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4316cb6f5e08c2f274343aeb8037c99
Publikováno v:
University of Southern Denmark
Neural Stochastic Differential Equations model a dynamical environment with neural nets assigned to their drift and diffusion terms. The high expressive power of their nonlinearity comes at the expense of instability in the identification of the larg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a12ec1ce73b522de6e1d4277fe64957e
http://arxiv.org/abs/2006.09914
http://arxiv.org/abs/2006.09914
Publikováno v:
IJCAI
University of Southern Denmark
University of Southern Denmark
Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is strictly i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f564182ec7b85657d5624f245a4e1194
http://arxiv.org/abs/1906.11471
http://arxiv.org/abs/1906.11471
Publikováno v:
University of Southern Denmark
We propose a novel method for closed-form predictive distribution modeling with neural nets. In quantifying prediction uncertainty, we build on Evidential Deep Learning, which has been impactful as being both simple to implement and giving closed-for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c0f737b5bc06e5b2a407656ecc305aa
http://arxiv.org/abs/1906.00816
http://arxiv.org/abs/1906.00816
Autor:
Jennifer M. Thompson, Manuel Haussmann, Tilman Plehn, Michel Luchmann, Gregor Kasieczka, Sven Bollweg
Publikováno v:
SciPost Physics, Vol 8, Iss 1, p 006 (2020)
Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers. We show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c924642ebba5fd4a96d1ebacc68b2ace
http://arxiv.org/abs/1904.10004
http://arxiv.org/abs/1904.10004
Autor:
Wan, Zhijing1 (AUTHOR) wanzjwhu@whu.edu.cn, Wang, Zhixiang2 (AUTHOR) wangzx1994@gmail.com, Chung, Cheukting1 (AUTHOR) 2271406579@qq.com, Wang, Zheng1 (AUTHOR) wangzwhu@whu.edu.cn
Publikováno v:
ACM Computing Surveys. Jul2024, Vol. 56 Issue 7, p1-34. 34p.