Title :
Learning as a multi-objective optimization in feedforward neural networks
Author :
A. Dumitras;V. Lazarescu;M. Negoita
Author_Institution :
Electron. & Telecommun. Dept., Politehnica Univ. of Bucharest, Romania
Abstract :
We prove that a multi-objective optimization approach of the learning process in feedforward neural networks leads to better signal processing performances in the presence of impulsive noise and outliers.
Keywords :
"Intelligent networks","Neural networks","Feedforward neural networks","Cost function","Noise robustness","Signal processing","Testing","Stability","Artificial neural networks","Probability density function"
Conference_Titel :
Knowledge-Based Intelligent Electronic Systems, 1997. KES ´97. Proceedings., 1997 First International Conference on
Print_ISBN :
0-7803-3755-7
DOI :
10.1109/KES.1997.619441
