Buscar
Mostrando ítems 1-10 de 1295
Posicionamento em ambientes não estruturados e treinamento de redes neurais utilizando filtros de Kalman
(Universidade Federal de São CarlosUFSCarPrograma de Pós-Graduação em Ciência da Computação - PPGCCCâmpus São Carlos, 2016-03-04)
Kalman filters are rooted in the technical literature, as a way of predicting new states in
nonlinear systems providing a recursive solution to the problem of linear optimal filtering.
Therefore, 56 years after its ...
Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
(Institute of Electrical and Electronics Engineers, 2005-03)
Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
(Institute of Electrical and Electronics Engineers, 2005-03)
Recurrent neural networks (RNNs) have been successfully applied to communications channel equalization because of their modeling capability for nonlinear dynamic systems. Major
problems of gradient-descent learning techniques ...