Quantum computing for pattern classification
Abstract
It is well known that for certain tasks, quantum computing outperforms classical computing. A growing number of contributions try to use this advantage in order to improve or extend classical machine learning algorithms by methods of quantum information theory. This paper gives a brief introduction into quantum machine learning using the example of pattern classification. We introduce a quantum pattern classification algorithm that draws on Trugenberger's proposal for measuring the Hamming distance on a quantum computer (CA Trugenberger, Phys Rev Let 87, 2001) and discuss its advantages using handwritten digit recognition as from the MNIST database.
Cite
@article{arxiv.1412.3646,
title = {Quantum computing for pattern classification},
author = {Maria Schuld and Ilya Sinayskiy and Francesco Petruccione},
journal= {arXiv preprint arXiv:1412.3646},
year = {2014}
}
Comments
14 pages, 3 figures, presented at the 13th Pacific Rim International Conference on Artificial Intelligence