Title :
Counterpropagation with delays for financial prediction
Author :
Fierascu, Carmen ; Badea, Claudia Lidia
Author_Institution :
Inst. of Sci. Comput., Salzburg Univ., Austria
Abstract :
The counterpropagation network was obtained by combining Kohonen learning and Grossberg learning. By adding of dynamical elements in the Kohonen learning, we obtained a new network, the counterpropagation neural network with delays. This network is suitable to be applied for solving problems in the domain of temporal sequence processing. An application to a financial prediction problem, the forecasting of the currency exchange rate, is shown.
Keywords :
delays; economic forecasting; learning (artificial intelligence); self-organising feature maps; Grossberg learning; Kohonen learning; counterpropagation neural network; delays; financial prediction; temporal sequence processing; Delay; Density functional theory; Electronic mail; Exchange rates; Function approximation; Neural networks; Neurons; Pattern matching; Predictive models; Scientific computing;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1381098
