Cargando…

Model-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production

<!--HTML-->We propose and demonstrate the use of a Model-Assisted Generative Adversarial Network to produce simulated images that accurately match true images through the variation of underlying model parameters that describe the image generation process. The generator learns the parameter val...

Descripción completa

Detalles Bibliográficos
Autor principal: Alonso Monsalve, Saul
Lenguaje:eng
Publicado: 2019
Materias:
Acceso en línea:http://cds.cern.ch/record/2672623
_version_ 1780962468442406912
author Alonso Monsalve, Saul
author_facet Alonso Monsalve, Saul
author_sort Alonso Monsalve, Saul
collection CERN
description <!--HTML-->We propose and demonstrate the use of a Model-Assisted Generative Adversarial Network to produce simulated images that accurately match true images through the variation of underlying model parameters that describe the image generation process. The generator learns the parameter values that give images that best match the true images. The best match parameter values that produce the most accurate simulated images can be extracted and used to re-tune the default simulation to minimise any bias when applying image recognition techniques to simulated and true images. In the case of a real-world experiment, the true data is replaced by experimental data with unknown true parameter values. The Model-Assisted Generative Adversarial Network uses a convolutional neural network to emulate the simulation for all parameter values that, when trained, can be used as a conditional generator for fast image production.
id cern-2672623
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2019
record_format invenio
spelling cern-26726232022-11-02T22:33:36Zhttp://cds.cern.ch/record/2672623engAlonso Monsalve, SaulModel-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production3rd IML Machine Learning WorkshopLPCC Workshops<!--HTML-->We propose and demonstrate the use of a Model-Assisted Generative Adversarial Network to produce simulated images that accurately match true images through the variation of underlying model parameters that describe the image generation process. The generator learns the parameter values that give images that best match the true images. The best match parameter values that produce the most accurate simulated images can be extracted and used to re-tune the default simulation to minimise any bias when applying image recognition techniques to simulated and true images. In the case of a real-world experiment, the true data is replaced by experimental data with unknown true parameter values. The Model-Assisted Generative Adversarial Network uses a convolutional neural network to emulate the simulation for all parameter values that, when trained, can be used as a conditional generator for fast image production.oai:cds.cern.ch:26726232019
spellingShingle LPCC Workshops
Alonso Monsalve, Saul
Model-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production
title Model-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production
title_full Model-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production
title_fullStr Model-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production
title_full_unstemmed Model-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production
title_short Model-Assisted GANs for the optimisation of simulation parameters and as an algorithm for fast Monte Carlo production
title_sort model-assisted gans for the optimisation of simulation parameters and as an algorithm for fast monte carlo production
topic LPCC Workshops
url http://cds.cern.ch/record/2672623
work_keys_str_mv AT alonsomonsalvesaul modelassistedgansfortheoptimisationofsimulationparametersandasanalgorithmforfastmontecarloproduction
AT alonsomonsalvesaul 3rdimlmachinelearningworkshop