Application of Artificial Neural Networks on improving predictions of nuclear radii

Autor:	V. Skarlis, Emmanuel Bratsolis, Eleni Charou, T. J. Mertzimekis
Rok vydání:	2018
Předmět:	Nonlinear system Artificial neural network business.industry Computer Science::Neural and Evolutionary Computation Evaluated data Neural system Artificial intelligence Machine learning computer.software_genre business computer Field (computer science) Mathematical Computing
DOI:	10.6084/m9.figshare.6449672
Popis:	Artificial Neural Networks (ANN) are mathematical computing paradigms imitating the operations of biological neural systems. Their nonlinear nature and ability to learn from the environment make them highly suited to solve real-world problems from those that are still under development. In the field of Physics there are many problems which cannot be adequately solved with the physics–based methods and the use of ANN may yield better results. In the present work ANNs have been tested in predicting nuclear radii considering as input the atomic and mass numbers, exclusively. The performance of different supervised ANNs is evaluated. The dataset used for the training and testing was based on evaluated data of nuclear radii available in IAEA tables.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::323735f98dd79c3ef4857be1602213df Zobrazit plný text záznamu