CNN based on multi-valued neuron as a model of associative memory for grey scale images
Naum N. Aizenberg, Igor N. Aizenberg · 2003
A mathematical model of multivalued neural elements that can be used as an alternative to the basic cellular neural network (CNN) element is presented. On the basis of such CNNs, a model of the associative memory for storing gray-scale images is given. An efficient learning algorithm for the neural element and associative memory is presented.>