Corrección de la Muestra para el Aprendizaje del Perceptron Multicapa

Barandela, Ricardo; Gasca, Eduardo; Alejo, R.

doi:10.4114/ia.v5i13.691

Cited by 1 publication

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural computing can be applied not only to classification or pattern recognition problems but also to problems involving function approximation in general [11,12]. The artificial NN is useful either to determine the category to which an object belongs or to identify the existing categories in a given set of objects [7,[13][14][15][16]. The main characteristic of neural systems is its adaptability, which creates a style of a completely new design of systems.…”

Section: Introductionmentioning

confidence: 99%

Neural networks for fitting PES data distributions of asphaltene interaction

Gasca

Pacheco

Álvarez

2009

2009 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

Neural networks methodology is a tool to get potential energy surface (PES) in cases where there is too much dispersion of data; hence, a binding energy fitting can be found with this methodology on asphaltene-asphaltene molecular interaction. A data distribution of intermolecular pair potential (U AA) interaction in a vacuum between two molecular asphaltenes systems using compass classical force field has been previously reported (Energy Fuels 2006, 20, 195). In the latter, all possible interactions between the species were taken into account. Focusing in their data distribution, we have applied neural networks on the following molecule-molecule geometry orientations with the purpose of obtaining energy vs. contact distance, which is the minimum distance where the interacting species is not equal to zero: i) face-to-face distribution of asphaltene-asphaltene interactions; ii) all geometry asphalteneasphaltene discrete distributions, and iii) the random distribution of asphaltene-asphaltene interactions. Neural networks fit provide a potential energy surface through a function approximation, for a data distribution of high dispersion; hence a binding energy is found with this methodology.

show abstract