Uncertainty of feed forward neural networks recognizing quantum contextuality
Authors:
Open Access
- 17 October 2023
- journal article
- research article
- Published by IOP Publishing in Journal of Physics A: Mathematical and Theoretical
- Vol. 56 (45) , 455305
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 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 datasets. 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.Keywords
All Related Versions
Funding Information
- IRAP project, ICTQT, (MAB/2018/5)
This publication has 37 references indexed in Scilit:
- Axiomatic approach to contextuality and nonlocalityPhysical Review A, 2015
- A Combinatorial Approach to Nonlocality and ContextualityCommunications in Mathematical Physics, 2015
- Contextuality supplies the ‘magic’ for quantum computationNature, 2014
- Bell nonlocalityReviews of Modern Physics, 2014
- Unified approach to contextuality, nonlocality, and temporal correlationsPhysical Review A, 2014
- All noncontextuality inequalities for the-cycle scenarioPhysical Review A, 2013
- Improving Zero-Error Classical Communication with EntanglementPhysical Review Letters, 2010
- Quantum entanglementReviews of Modern Physics, 2009
- Aleatory or epistemic? Does it matter?Structural Safety, 2009
- Simple Test for Hidden Variables in Spin-1 SystemsPhysical Review Letters, 2008