Quantum enhanced cross-validation for near-optimal neural networks architecture selection

TL;DR

This paper introduces a quantum-classical algorithm leveraging quantum superposition and probabilistic quantum memory to evaluate and select neural network architectures, achieving exponential speedup and near-optimal selection.

Contribution

It presents a novel quantum-enhanced method for neural network architecture selection, combining quantum superposition with classical evaluation techniques.

Findings

Achieves exponential quantum speedup in neural network evaluation.

Demonstrates potential for near-optimal architecture selection.

Validates the approach through reduced experimental analysis.

Abstract

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.