A quantum speedup in machine learning: finding an N-bit Boolean function for a classification

Abstract

We compare quantum and classical machines designed for learning an N-bitBoolean function in order to address how a quantum system improves themachine learning behavior. The machines of the two types consist of the samenumber of operations and control parameters, but only the quantum machinesutilize the quantum coherence naturally induced by unitary operators. We showthat quantum superposition enables quantum learning that is faster than classicallearning by expanding the approximate solution regions, i.e., the acceptableregions. This is also demonstrated by means of numerical simulations with astandard feedback model, namely random search, and a practical model, namelydifferential evolution.