Uncertainty of feed forward neural networks recognizing quantum contextuality

DOI10.1088/1751-8121/ACFD6BMaRDI QIDQ6063374zbMATH OpenOpenAlexFDO

Authors Tomasz Paterek, Karol Horodecki

Publication date 7 November 2023

Published in Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2212.13564

zbMATH Keywords

Bayesian neural networkscontextualityuncertainty of neural networks

Mathematics Subject Classification ID

Computer science (68-XX) Quantum theory (81-XX)

Abstract: The usual figure of merit characterizing the performance of neural networks applied to problems in the quantum domain is their accuracy, being the probability of a correct answer on a previously unseen input. Here we append this parameter with the uncertainty of the prediction, characterizing the degree of confidence in the answer. A powerful technique for estimating both the accuracy and the uncertainty is provided by Bayesian neural networks (BNNs). We first give simple illustrative examples of advantages brought forward by BNNs, out of which we wish to highlight their ability of reliable uncertainty estimation even after training with biased data sets. Then we apply BNNs to the problem of recognition of quantum contextuality which shows that the uncertainty itself is an independent parameter identifying the chance of misclassification of contextuality.

Recommendations

• Uncertainty quantification in neural network classifiers -- a local linear approach
• scientific article; zbMATH DE number 1691472
• Quantifying unknown entanglement by neural networks
• Some quantum neural networks

Cites work

• A combinatorial approach to nonlocality and contextuality
• Bayesian learning for neural networks
• Deep learning
• Gradient Theory of Optimal Flight Paths
• scientific article; zbMATH DE number 3251317 (Why is no real title available?)
• Multilayer feedforward networks are universal approximators
• Probabilistic machine learning. An introduction
• Proposed experiment to test local hidden-variable theories
• Quantum -entropy inequalities: independent condition for local realism?
• Quantum advantage with shallow circuits
• Quantum entanglement
• Simple test for hidden variables in spin-1 systems
• Simple unified form for the major no-hidden-variables theorems

Cited in

(3)

• Quantifying unknown entanglement by neural networks
• Can a single neuron learn predictive uncertainty?
• Uncertainty quantification in neural network classifiers -- a local linear approach

This page was built for publication: Uncertainty of feed forward neural networks recognizing quantum contextuality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6063374)