Analog quantum neuron for functions approximation
Alexandr Alexandrovich Ezhov, Andrey Grigorievich Khromov, G. P. Berman · 2002
We describe a system which is able to perform universal stochastic approximations of continuous multivariable functions in both neuron-like and quantum manner. The implementation of this model in the form of multi-barrier multiple-silt system has been earlier proposed. For the simplified waveguide variant of this model it is proved, that the system can approximate any continuous function of many variables. This theorem is also applied to the 2-input quantum neural model analogical to the schemes developed for quantum control.