Quantum space distance estimation for classifier training using hybrid classical-quantum computing system

Abstract

Hybrid classical-quantum decision maker training includes receiving a training data set, and selecting, by a first processor, a sampling of objects from the training set, each object represented by at least one vector. A quantum processor applies a quantum feature map to the selected objects to produce one or more output vectors. The first processor determines one or more distance measures between pairs of the output vectors, and determines at least one portion of the quantum feature map to modify the classical feature map. The first processor adds an implementation of the at least one portion of the quantum feature map to the classical feature map to generate an updated classical feature map.