Title :
On the mapping capacity of feedforward neural networks
Author :
Wei, Gang ; Kwong, Sam ; Man, K.F.
Author_Institution :
Inst. of Radio Eng. & Control, South China Univ. of Technol., Guangzhou, China
Abstract :
This paper addresses the mapping capacity of feedforward neural networks (FFNNs). We propose a new condition of the activation function for FFNNs to be capable of approximating any continuous maps defined on ℜn. Based on the result, we construct several FFNN based nonlinear predictors for speech signals, and study their performances
Keywords :
approximation theory; feedforward neural nets; function approximation; prediction theory; speech processing; speech recognition; activation function; feedforward neural networks; mapping capacity; nonlinear predictors; speech signals; Application software; Computer science; Feedforward neural networks; Feeds; Input variables; Neural networks; Polynomials; Speech;
Conference_Titel :
Systems, Man and Cybernetics, 1995. Intelligent Systems for the 21st Century., IEEE International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-2559-1
DOI :
10.1109/ICSMC.1995.537804
