| Abstract [eng] |
The analysis of a chaos theory, in general, and a neural network chaos paradigm with a concrete interpretation by a simple neural network, in particular, allowed us to set up a new aspect in an artificial neuronal approach of methodology: an analogy between natural chaos experimentally observed in neural systems of the brain and artificial neural network chaos phenomena has been considered. The significance of asymmetry and nonlinearity, which were increased on introducing a restricted N-shaped synaptical relation in a two-mod dynamic model, is emphasized. There are illustrated the diferent computational examples of the neural network properties which are expressed by the equillibrium point, stable cycle or chaotic behaviour in strong nonlinear neural systems. |
