Title :
Scale-rule selection of affordable neural network for chaotic time series learning
Author :
Uwate, Yoko ; Nishio, Yoshifumi ; Stoop, Ruedi
Author_Institution :
Dept. of Electr. & Electron. Eng., Tokushima Univ., Tokushima
Abstract :
Scale-free networks are an important class of complex networks since many "real-world networks" fall into this category. In our contribution we investigate the influence of this property on the performance of an affordable neural network. y means of computer simulations, we confirm that affordable neural networks, when the affordable neurons are chosen in a scale-free manner, perform significantly better compared to random selection.
Keywords :
chaos; neural nets; time series; chaotic time series learning; neural network; random selection; scale-free manner; scale-rule selection; Biological neural networks; Chaos; Complex networks; Computer simulation; Convergence; Displays; Neural networks; Neurons; Power engineering and energy; Power generation economics;
Conference_Titel :
Circuit Theory and Design, 2007. ECCTD 2007. 18th European Conference on
Conference_Location :
Seville
Print_ISBN :
978-1-4244-1341-6
Electronic_ISBN :
978-1-4244-1342-3
DOI :
10.1109/ECCTD.2007.4529720
