Método de segmentações geométricas sucessivas para treinamento de redes neurais artificiais
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Universidade Federal de Juiz de Fora (UFJF)
DOI
Abstract
This work presents a technique for Artificial Neural Network (ANN) training, able to get the network parameters from the available data for training, without establishing the network architecture a priori, called Successive Geometric Segmentation Method (SGSM). The SGSM groups the data of each class into hyperboxes (HB) aligned in accordance with the largest axis of its points distribution. If the HB are linearly separable, a separating hyperplane may be identified resulting a neuron. If it is not, a segmentation technique is applied to divide the data into smaller classes for new HB. For each subdivision new neurons are added to the network. The tests show a rapid method with high success rate.
Description
Keywords
Rede neural artificial , Reconhecimento de padrões , Teorema do hiperplano de separação , Hipercaixas , Segmentação geométrica sucessiva , Auto-geração de neurônio , Artificial neural nets , Patterns classification , Hyperplane separation theorem , Hyperbox , Successive geometric segmentation , Self-generation of neuron
Citation
Endorsement
Review
Supplemented By
Referenced By
Rights and licensing
Acesso Aberto
