Neural networks regularization with graph-based local resampling.

Simple item page
dc.contributor.authorAssis, Alex Damiany
dc.contributor.authorTorres, Luiz Carlos Bambirra
dc.contributor.authorAraújo, Lourenço Ribeiro Grossi
dc.contributor.authorHanriot, Vítor Mourão
dc.contributor.authorBraga, Antônio Pádua
dc.date.accessioned2022-09-15T18:11:20Z
dc.date.available2022-09-15T18:11:20Z
dc.date.issued2021pt_BR
dc.description.abstractThis paper presents the concept of Graph-based Local Resampling of perceptron-like neural networks with random projections (RN-ELM) which aims at regularization of the yielded model. The addition of synthetic noise to the learning set finds some similarity with data augmentation approaches that are currently adopted in many deep learning strategies. With the graph-based approach, however, it is possible to direct resample in the margin region instead of exhaustively cover the whole input space. The goal is to train neural networks with added noise in the margin region, located by structural information extracted from a planar graph. The so-called structural vectors, which are the training set vertices near the class boundary, are obtained from the structural information using Gabriel Graph. Synthetic samples are added to the learning set around the geometric vectors, improving generalization performance. A mathematical formulation that shows that the addition of synthetic samples has the same effect as the Tikhonov regularization is presented. Friedman and pos-hoc Nemenyi tests indicate that outcomes from the proposed method are statistically equivalent to the ones obtained by objective-function regularization, implying that both methods yield smoother solutions, reducing the effects of overfitting.pt_BR
dc.identifier.citationASSIS, A. D. et al. Neural networks regularization with graph-based local resampling. IEEE Access, v. 9, p. 50727-50737, 2021. Disponível em: <https://ieeexplore.ieee.org/document/9383228>. Acesso em: 29 abr. 2022.pt_BR
dc.identifier.doihttps://doi.org/10.1109/ACCESS.2021.3068127pt_BR
dc.identifier.issn2169-3536
dc.identifier.urihttp://www.repositorio.ufop.br/jspui/handle/123456789/15295
dc.language.isoen_USpt_BR
dc.rightsabertopt_BR
dc.rights.licenseThis work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/. Fonte: o PDF do artigo.pt_BR
dc.subjectClassifierpt_BR
dc.subjectTraining with noisept_BR
dc.titleNeural networks regularization with graph-based local resampling.pt_BR
dc.typeArtigo publicado em periodicopt_BR
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
ARTIGO_NeuralNetworksRegularization.pdf
Size:
1.91 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
DECSI - Artigos publicados em periódicos