info:eu-repo/semantics/article
Dynamical Functional Artificial Neural Network: Use of Efficient Piecewise Linear Functions
Fecha
2008-12Registro en:
Figueroa, Jose Luis; Cousseau, Juan Edmundo; Dynamical Functional Artificial Neural Network: Use of Efficient Piecewise Linear Functions; Planta Piloto de Ingeniería Química; Latin American Applied Research; 38; 2; 12-2008; 187-193
0327-0793
1851-8796
CONICET Digital
CONICET
Autor
Figueroa, Jose Luis
Cousseau, Juan Edmundo
Resumen
A nonlinear adaptive time series predictor has been developed using a new type of piecewise linear (PWL) network for its underlying model structure. The PWL Network is a D-FANN (Dynamical Functional Artificial Neural Network) the activation functions of which are piecewise linear. The new realization is presented with the associated training algorithm. Properties and characteristics are discussed. This network has been successfully used to model and predict an important class of highly dynamic and nonstationary signals, namely speech signals.