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

DOI10.1142/S0219749918400051zbMATH Open1407.81060arXiv1808.09058MaRDI QIDQ4620293FDOQ4620293

Authors: Priscila G. M. dos Santos, Rodrigo S. Sousa, I. C. Araújo, Adenilton J. da Silva 

Publication date: 8 February 2019

Published in: International Journal of Quantum Information (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1808.09058

Recommendations

• Quantum \(k\)-fold cross-validation for nearest neighbor classification algorithm
• Neural networks with quantum architecture and quantum learning
• Quantum neural networks
• Quantum neural nets
• Quantum perceptron over a field and neural network architecture selection in a quantum computer
• A GNN-based predictor for quantum architecture search
• Quantum neural network
• Quantum artificial neural network architectures and components
• Some quantum neural networks
• Quantum artificial neural networks with applications

zbMATH Keywords

cross-validationparameter selectionquantum neural networksquantum machine learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Quantum computation (81P68) Memory and learning in psychology (91E40) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Cites Work

• Scikit-learn: machine learning in Python
• Learning representations by back-propagating errors
• Title not available (Why is that?)
• A logical calculus of the ideas immanent in nervous activity
• A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training
• Title not available (Why is that?)
• The quest for a quantum neural network
• Neural networks for applied sciences and engineering. From fundamentals to complex pattern recognition.
• Neural networks with quantum architecture and quantum learning
• Title not available (Why is that?)
• Quantum perceptron over a field and neural network architecture selection in a quantum computer

Cited In (10)

• Quantum-enhanced feature selection with forward selection and backward elimination
• Prospects of quantum-classical optimization for digital design
• QUANTUM COMPUTATION FOR ACTION SELECTION USING REINFORCEMENT LEARNING
• Quantum \(k\)-fold cross-validation for nearest neighbor classification algorithm
• Iris Data Classification Using Quantum Neural Networks
• Explicit demonstration of initial state construction in artificial neural networks using netket and IBM Q experience platform
• A GNN-based predictor for quantum architecture search
• Evolution strategies: application in hybrid quantum-classical neural networks
• Optimization of the memory reset rate of a quantum echo-state network for time sequential tasks
• Efficient quantum feature extraction for CNN-based learning

Uses Software

• Adam
• openQASM

This page was built for publication: Quantum enhanced cross-validation for near-optimal neural networks architecture selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4620293)