Learning regularization parameters of radial basis functions in embedded likelihoods space

Página do item simplificado
dc.creatorMurilo Queiroz
dc.creatorLuiz Carlos Bambirra Torres
dc.creatorAntonio de Padua Braga
dc.date.accessioned2025-05-07T14:53:08Z
dc.date.accessioned2025-09-09T00:14:54Z
dc.date.available2025-05-07T14:53:08Z
dc.date.issued2019
dc.identifier.urihttps://hdl.handle.net/1843/82092
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofProgress in Artificial Intelligence (EPIA 2019)
dc.rightsAcesso Restrito
dc.subjectRedes neurais (Computação)
dc.subject.otherFor valid generalization the size of the weights is more important than the size of the network
dc.subject.otherOrthogonal least squares learning algorithm for radial basis function networks
dc.subject.otherStatistical comparisons of classifiers over multiple data sets
dc.titleLearning regularization parameters of radial basis functions in embedded likelihoods space
dc.typeArtigo de evento
local.citation.epage292
local.citation.spage281
local.description.resumoNeural networks with radial basis activation functions are typically trained in two different phases: the first consists in the construction of the hidden layer, while the second consists in finding the output layer weights. Constructing the hidden layer involves defining the number of units in it, as well as their centers and widths. The training process of the output layer can be done using least squares methods, usually setting a regularization term. This work proposes an approach for building the whole network using information extracted directly from the projected training data in the space formed by the likelihoods functions. One can, then, train RBF networks for pattern classification with minimal external intervention.
local.publisher.countryBrasil
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELETRÔNICA
local.publisher.initialsUFMG
local.url.externahttps://link.springer.com/chapter/10.1007/978-3-030-30244-3_24

Arquivos

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Evento

Logo UFMG