A quantum self-organizing mapping neural network

This paper addresses the training dead zone problem of the self-organizing map (SOM) neural network using quantum technology. A new quantum SOM neural model with elastic neighborhood radius is proposed. The new model objects the real input data into the quantum initial states. Through the operation of the quantum gate in the qubit neuron, the the quantum initial states are converted into the quantum intermediate states, then into the quantum excited sates. These excited sates, being connected with the quantized weights, are perceived by the competitive-layer neurons. According to a new quantized competitive learning algorithm, the input data can be orderly topology mapped. The elastic neighborhood radius, in the new learning algorithm, is defined by both of the similarity and the distance between quantized weights and quantum excited states. It avoids some of the competitive-layer neurons form the dead zone due to a fixed radius scaling. The numerical experiments verify the effectiveness of this new neural model.