| 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 |