Title :
Pattern dynamics of chaotic neural networks with nearest-neighbor couplings
Author :
Adachi, M. ; Aihara, K. ; Kotani, M.
Author_Institution :
Dept. of Electron. Eng., Tokyo Denki Univ., Japan
Abstract :
The authors introduce chaos into simple mathematical neuron models which are deterministic rather than probabilistic. The authors apply chaotic dynamics to artificial neural networks, using a chaotic neuron model based on electrophysiological experiments with squid giant axons and on numerical experiments with the Hodgkin-Huxley equations. First, the authors explain the chaotic neuron model and its dynamics. The authors also demonstrate spatio-temporal pattern dynamics of chaotic neural networks with nearest-neighbor couplings. It is shown that the chaotic neural networks with nearest-neighbor couplings have abundant spatio-temporal dynamics with a possible applicability to dynamical spatio-temporal memory
Keywords :
brain models; chaos; neural nets; pattern recognition; Hodgkin-Huxley equations; artificial neural networks; chaotic dynamics; chaotic neural networks; chaotic neuron model; dynamical spatio-temporal memory; electrophysiological experiments; mathematical neuron models; nearest-neighbor couplings; spatio-temporal pattern dynamics; squid giant axons; Artificial neural networks; Bifurcation; Biological neural networks; Chaos; Equations; Integrated circuit modeling; Multi-layer neural network; Neural networks; Neurofeedback; Neurons;
Conference_Titel :
Circuits and Systems, 1991., IEEE International Sympoisum on
Print_ISBN :
0-7803-0050-5
DOI :
10.1109/ISCAS.1991.176578