Title :
Chaotic wandering and its sensitivity to external input in a chaotic neural network
Author :
Kuroiwa, J. ; Masutani, N. ; Nara, S. ; Aihara, K.
Author_Institution :
Dept. of Human & Artificial Intelligent Syst., Fukui Univ., Japan
Abstract :
Dynamical properties of chaotic neural network in chaotic wandering state are studied concerning sensitivity to external inputs. The number of the attractor basins which time dependent vector can visit during chaotic wandering depends on the dynamical complexity of chaos. When one applies the external input consisting of a memory fragment to the network, within several iteration steps the orbit reach the basin of the memory attractor.
Keywords :
chaos; dynamics; iterative methods; neural nets; sensitivity analysis; attractor basins; chaotic neural network; chaotic wandering state; dynamical properties; external inputs sensitivity; iterative method; pseudo-inverse method; time dependent vector; Artificial neural networks; Biological neural networks; Cellular neural networks; Chaos; Educational technology; Humans; Intelligent networks; Neural networks; Neurons; State-space methods;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1202192
