Looking for the lost noise

The noise can be very well approximated using a simple circuit and a sophisticated rule. We propose a simple, recursively defined, big circuit that, starting from own autonomy, generates pseudo-noise. To the well known method of using cellular automaton in order to generate pseudo-random sequences some new features are added in order to improve the "random" behaviour. The randomness results in a chaotic process, very sensible to the initial state of a simple machine working after a strange rule. The proposed structure claims a huge amount of work in order to find an appropriate initial state according to tire noise "characteristics". The initial state must be selected from a space having 2/sup 256/ points. Only the genetic algorithms offers us the illusion of finding the best point in this huge space.