Title :
Symmetric properties of neural networks for control applications
Author_Institution :
Res. Center, Daimler-Benz AG, Ulm, Germany
fDate :
27 Jun-2 Jul 1994
Abstract :
Applications of neural networks to control impose hard constraints on the symmetric properties of the functional that is to be learned by a neural network. Traditional sigmoid units are not able to satisfy these constraints. A new type of unit, the modulated sigmoid unit, is presented that can simultaneously represent symmetries with regard to some inputs and asymmetries to others. The importance of symmetric relationships and the use of this unit is illustrated on applications to control and system identification
Keywords :
identification; neural nets; neurocontrollers; modulated sigmoid unit; neural control; neural networks; symmetric properties; symmetries; system identification; Control systems; Neural networks; Nonlinear control systems; Pattern recognition; System identification;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374704
