SANNET: Image compression and regeneration by nonlinear associative silicon retina

Describes image compression and regeneration by a novel nonlinear associative retina chip which is a sparse neural network. This retina chip is a dual network of a Hopfield cellular network. The input information sequences are given to links as currents. The error-correcting capacity (minimum basins of attraction) is decided by the minimum numbers of links of loop. The operation principle of the regeneration is based on current distribution of the neural field. The most important nonlinear operation is a dynamic quantization to decide the binary value of each neuron output from the neighbor value. The rates of compression used in the simulation are 2/3×1/8, where 2/3 and 1/8 are the rates of structural and the binarizational compression, respectively