Neural cooperating procedure for fractal analysis of artificial drawings

We assess a procedure for discovering the mixing ratios of transformations within the bench of affine maps of a probabilistic iterated fuzzy functions system which gives rise to 256 artificial color drawings. A first hypothesis on these ratios is obtained from a pseudo-ergodic estimate of the probabilities of matching special paths during the image generation. The job of the neural network is to remove biases from this hypothesis after a proper training. The reconstructed images are nearly identical to their original ones also on instances not used to train the network, and their representation through the above ratios attains a very high compression rate.