Empirical fits to inclusive electron-carbon scattering data obtained by deep-learning methods

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kowal, Beata E., Graczyk, Krzysztof M., Ankowski, Artur M., Banerjee, Rwik Dharmapal, Prasad, Hemant, Sobczyk, Jan T.
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911956367048704
author Kowal, Beata E.
Graczyk, Krzysztof M.
Ankowski, Artur M.
Banerjee, Rwik Dharmapal
Prasad, Hemant
Sobczyk, Jan T.
author_facet Kowal, Beata E.
Graczyk, Krzysztof M.
Ankowski, Artur M.
Banerjee, Rwik Dharmapal
Prasad, Hemant
Sobczyk, Jan T.
contents Employing the neural network framework, we obtain empirical fits to the electron-scattering cross sections for carbon over a broad kinematic region, extending from the quasielastic peak through resonance excitation to the onset of deep-inelastic scattering. We consider two different methods of obtaining such model-independent parametrizations and the corresponding uncertainties: based on the bootstrap approach and the Monte Carlo dropout approach. In our analysis, the $χ^2$ defines the loss function, including point-to-point and normalization uncertainties for each independent set of measurements. Our statistical approaches lead to fits of comparable quality and similar uncertainties of the order of $7$%. To test these models, we compare their predictions to test datasets excluded from the training process and theoretical predictions obtained within the spectral function approach. The predictions of both models agree with experimental measurements and theoretical calculations. We also perform a comparison to a dataset lying beyond the covered kinematic region, and find that the bootstrap approach shows better interpolation and extrapolation abilities than the one based on the dropout algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17298
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Empirical fits to inclusive electron-carbon scattering data obtained by deep-learning methods
Kowal, Beata E.
Graczyk, Krzysztof M.
Ankowski, Artur M.
Banerjee, Rwik Dharmapal
Prasad, Hemant
Sobczyk, Jan T.
High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
Nuclear Experiment
Nuclear Theory
Employing the neural network framework, we obtain empirical fits to the electron-scattering cross sections for carbon over a broad kinematic region, extending from the quasielastic peak through resonance excitation to the onset of deep-inelastic scattering. We consider two different methods of obtaining such model-independent parametrizations and the corresponding uncertainties: based on the bootstrap approach and the Monte Carlo dropout approach. In our analysis, the $χ^2$ defines the loss function, including point-to-point and normalization uncertainties for each independent set of measurements. Our statistical approaches lead to fits of comparable quality and similar uncertainties of the order of $7$%. To test these models, we compare their predictions to test datasets excluded from the training process and theoretical predictions obtained within the spectral function approach. The predictions of both models agree with experimental measurements and theoretical calculations. We also perform a comparison to a dataset lying beyond the covered kinematic region, and find that the bootstrap approach shows better interpolation and extrapolation abilities than the one based on the dropout algorithm.
title Empirical fits to inclusive electron-carbon scattering data obtained by deep-learning methods
topic High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
Nuclear Experiment
Nuclear Theory
url https://arxiv.org/abs/2312.17298