STATISTICAL QUANTUM NEURAL NETWORKS

Abstract

We explain a new idea of how to use the high probability interval thresholds for neurons in quantum neural networks. Some basic quantum neural networks were analyzed and constructed in a recent work of the author. In particular the Least Square Error Problem (LSEP) and the Linear Regression Problem (LRP) was discussed. In this paper we an- alyze a new look on the threshold rules for neurons, taking the intervals of high probability in place of classical sigmoid half-line threshold and then we construct the least-square quantum neural network (LS-QNN), the poly- nomial interpolation quantum neural network (PI-QNN), the polynomial regression quantum neural network (PR-QNN) and chi-squared quantum neural network (X²-QNN). We use the corresponding solutions or statistical tests as the threshold for the corresponding training rules.