Scale-rule selection of affordable neural network for chaotic time series learning
Yoko Uwate, Yoshifumi Nishio, Ruedi Stoop · 2007
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.