By introducing quantum superposition into neural networks,this paper proposes a model of quantum neural network,in which the units in the hidden and output layers adopt the superposition of multi-level activation functions to obtain the multi-lever partitions of the feature space.

For that from several levels of the sub-wave-front two-beam interference,double-slit diffraction,double-slit filter and double-slit quantum superposition,on the initial theory of Young\'s experiment is discussed in favor of optical theory and technology development.