Local noise in neural networks models with self-control

We modify neural networks models of the Hopfield type so that they can recognize the degree of novelty of the input stimuli on a local level. The networks control themselves the quality of recognition and can also recognize locally the bits of information in the input patterns which do not agree with known patterns, i.e. stored memories. This task is achieved by introducing local variations of the noise level beta in the network. Noise level in a given location depends on the flip frequency of the neurons close to that location.