CERN Accelerating science

CERN Document Server 2,026 registres trobats  1 - 10següentfinal  anar al registre: La cerca s'ha fet en 0.58 segons. 
1.
Direct Evolutionary Optimization of Variational Autoencoders with Binary Latents / Drefs, Jakob (Oldenburg U.) ; Guiraud, Enrico (CERN) ; Panagiotou, Filippos (Oldenburg U.) ; Lücke, Jörg (Oldenburg U.)
Many types of data are generated at least partly by discrete causes. Deep generative models such as variational autoencoders (VAEs) with binary latents consequently became of interest. [...]
2023
In : European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2022), Grenoble, France, 19 - 23 Sep 2022, pp.357–372
2.
Evolutionary Variational Optimization of Generative Models / Drefs, Jakob (Oldenburg U.) ; Guiraud, Enrico (CERN) ; Lücke, Jörg (Oldenburg U.) ; Wood, Frank (ed.)
We combine two popular optimization approaches to derive learning algorithms for generative models: variational optimization and evolutionary algorithms. The combination is realized for generative models with discrete latents by using truncated posteriors as the family of variational distributions. [...]
2022 - 51 p. - Published in : J. Mach. Learn. Res.: 23 (2022) , pp. 1-51 Fulltext: PDF; External link: Fulltext
3.
Scalable Unsupervised Learning for Deep Discrete Generative Models / Guiraud, Enrico
Efficient, scalable training of probabilistic generative models is a highly sought after goal in the field of machine learning [...]
CERN-THESIS-2020-356 - University of Oldenburg : University of Oldenburg, 2021-02-02. - 136 p.

4.
Evolutionary expectation maximization / Guiraud, Enrico (Oldenburg U. ; CERN) ; Drefs, Jakob (Oldenburg U.) ; Lücke, Jörg (Oldenburg U.)
We establish a link between evolutionary algorithms (EAs) and learning of probabilistic generative models with binary hidden variables. Learning is formulated as approximate maximum likelihood optimization using variational expectation maximization. [...]
2018 - 8 p. - Published in : 10.1145/3205455.3205588
In : Genetic and Evolutionary Computation Conference (GECCO '18), Kyoto, Japan, 15 - 19 Jul 2018, pp.442-449
5.
Inference and Learning in a Latent Variable Model for Beta Distributed Interval Data / Mousavi, Hamid ; Buhl, Mareike (Oldenburg U.) ; Guiraud, Enrico (Oldenburg U. ; CERN) ; Drefs, Jakob (Oldenburg U.) ; Lücke, Jörg (Oldenburg U.)
Latent Variable Models (LVMs) are well established tools to accomplish a range of different data processing tasks. Applications exploit the ability of LVMs to identify latent data structure in order to improve data (e.g., through denoising) or to estimate the relation between latent causes and measurements in medical data. [...]
2021 - 28 p. - Published in : Entropy 23 (2021) 552 Fulltext: PDF;
6.
THE SUCCESS OF DEEP GENERATIVE MODELS / Tomczak, Jakub (speaker) (University of Amsterdam)
Deep generative models allow us to learn hidden representations of data and generate new examples. There are two major families of models that are exploited in current applications: Generative Adversarial Networks (GANs), and Variational Auto-Encoders (VAE). [...]
2018 - 3232. EP-IT Data science seminars External link: Event details In : THE SUCCESS OF DEEP GENERATIVE MODELS
7.
Anomaly Detection With Conditional Variational Autoencoders / Pol, Adrian Alan (CERN ; LRI, Paris 11) ; Berger, Victor (LRI, Paris 11) ; Cerminara, Gianluca (CERN) ; Germain, Cecile (LRI, Paris 11) ; Pierini, Maurizio (CERN)
Exploiting the rapid advances in probabilistic inference, in particular variational Bayes and variational autoencoders (VAEs), for anomaly detection (AD) tasks remains an open research question. [...]
arXiv:2010.05531.
- 8 p.
Fulltext
8.
Deep Generative Models for Fast Shower Simulation with the ATLAS Experiment / Raine, Johnny (Universite de Geneve (CH)) /ATLAS Collaboration
Modeling the physics of a detector's response to particle collisions is one of the most CPU intensive and time consuming aspects of LHC computing. With the upcoming high-luminosity upgrade and the need to have even larger simulated datasets to support physics analysis, the development of new faster simulation techniques but with sufficiently accurate physics performance is required. [...]
ATL-SOFT-SLIDE-2019-774.- Geneva : CERN, 2019 - 1 p. Fulltext: PDF; External link: Original Communication (restricted to ATLAS)
In : 24th International Conference on Computing in High Energy and Nuclear Physics, Adelaide, Australia, 4 - 8 Nov 2019
9.
Event Generation and Statistical Sampling with Deep Generative Models / Otten, Sydney (speaker) (Radboud Universiteit Nijmegen)
We present a study for the generation of events from a physical process with generative deep learning. To simulate physical processes it is not only important to produce physical events, but also to produce the events with the right frequency of occurrence (density). [...]
2019 - 1502. LPCC Workshops; 3rd IML Machine Learning Workshop External links: Talk details; Event details In : 3rd IML Machine Learning Workshop
10.
Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders / Touranakou, Mary (CERN ; Athens Natl. Capodistrian U.) ; Chernyavskaya, Nadezda (CERN) ; Duarte, Javier (UC, San Diego) ; Gunopulos, Dimitrios (Athens Natl. Capodistrian U.) ; Kansal, Raghav (UC, San Diego) ; Orzari, Breno (U. Sao Paulo (main)) ; Pierini, Maurizio (CERN) ; Tomei, Thiago (U. Sao Paulo (main)) ; Vlimant, Jean-Roch (Caltech)
We study how to use Deep Variational Autoencoders for a fast simulation of jets of particles at the LHC. We represent jets as a list of constituents, characterized by their momenta. [...]
arXiv:2203.00520; FERMILAB-PUB-22-954-V.- 2022-07-13 - 11 p. - Published in : Mach. Learn. Sci. Tech. 3 (2022) 035003 Fulltext: 2203.00520 - PDF; c3fccde8a2a4bc07788a1cc9d630587c - PDF; Fulltext from Publisher: PDF; External link: Fermilab Library Server

No heu trobat el que estaveu cercant? Proveu la vostra cerca a:
recid:2892139 dins Amazon
recid:2892139 dins CERN EDMS
recid:2892139 dins CERN Intranet
recid:2892139 dins CiteSeer
recid:2892139 dins Google Books
recid:2892139 dins Google Scholar
recid:2892139 dins Google Web
recid:2892139 dins IEC
recid:2892139 dins IHS
recid:2892139 dins INSPIRE
recid:2892139 dins ISO
recid:2892139 dins KISS Books/Journals
recid:2892139 dins KISS Preprints
recid:2892139 dins NEBIS
recid:2892139 dins SLAC Library Catalog