This paper proposes a quantum-classical algorithm to evaluate and select classical artificial neural networks architectures. The proposed algorithm is based on a probabilistic quantum memory and the possibility to train artificial neural networks in superposition. We obtain an exponential quantum speedup in the evaluation of neural networks. We also verify experimentally through a reduced experimental analysis that the proposed algorithm can be used to select near-optimal neural networks.
@article{arxiv.1808.09058,
title = {Quantum enhanced cross-validation for near-optimal neural networks architecture selection},
author = {Priscila G. M. dos Santos and Rodrigo S. Sousa and Ismael C. S. Araujo and Adenilton J. da Silva},
journal= {arXiv preprint arXiv:1808.09058},
year = {2018}
}