Quantum enhanced cross-validation for near-optimal neural networks architecture selection
This addresses the computational bottleneck in neural architecture search for machine learning practitioners, offering a potentially transformative but currently incremental advance due to limited experimental verification.
The paper tackles the problem of selecting optimal neural network architectures by proposing a quantum-classical algorithm that uses probabilistic quantum memory and superposition training, achieving an exponential quantum speedup in evaluation and experimentally demonstrating near-optimal selection.
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.