Busca avançada
Ano de início
Entree


Quaternion-valued recurrent projection neural networks on unit quaternions

Texto completo
Autor(es):
Valle, Marcos Eduardo ; Lobo, Rodolfo Anibal
Número total de Autores: 2
Tipo de documento: Artigo Científico
Fonte: THEORETICAL COMPUTER SCIENCE; v. 843, p. 17-pg., 2020-12-02.
Resumo

Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly, the QRPNNs are obtained by combining the non-local projection learning with the quaternion-valued recurrent correlation neural network (QRCNNs). We show that the QRPNNs overcome the cross-talk problem of the QRCNNs. Thus, they are appropriate to implement associative memories. Furthermore, computational experiments reveal that the QRPNNs exhibit greater storage capacity and noise tolerance than their corresponding QRCNNs. (c) 2020 Elsevier B.V. All rights reserved. (AU)

Processo FAPESP: 19/02278-2 - Morfologia Matemática e Redes Neurais Morfológicas para Dados Multi-valorados
Beneficiário:Marcos Eduardo Ribeiro Do Valle Mesquita
Modalidade de apoio: Auxílio à Pesquisa - Regular