Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Lecture notes in computer science

Linear Structure of Training Samples in Quantum Neural Network Applications

Alexander Mandl, Johanna Barzen, Marvin Bechtold, Michael Keckeisen, Frank Leymann, Patrick K. S. Vaudrevange

Published Jan 1, 2024• 4 citations
Publisher
DOI
10.1007/978-981-97-0989-2_12

Related papers

Quantum Neural Networks: Exploring Quantum Enhancements in Deep Learning

Dukuru Chiranjevi, Anisha Mishra, Ranjan Kumar Behera +1 more

Intelligent systems reference library•Jan 1, 2025•5 citations

On reducing the amount of samples required for training of QNNs: constraints on the linear structure of the training data

Alexander Mandl, Johanna Barzen, Frank Leymann +1 more

Abstract Training classical neural networks generally requires a large number of training samples. Using entangled training samples, Quantum Neural Networks (QNNs) have the potential to significantly reduce the amount of training samples required in the training process. However, to minimize the number of incorrect predictions made by the resulting QNN, it is essential that the structure of the training samples meets certain requirements. On the one hand, the exact degree of entanglement must be fixed for the whole set of training samples. On the other hand, training samples must be linearly independent and non-orthogonal. However, how failing to meet these requirements affects the resulting QNN is not fully studied. To address this, we extend the proof of the Quantum No-Free-Lunch theorem to (i) provide a generalization of the theorem for varying degrees of entanglement. This generalization shows that the average degree of entanglement in the set of training samples can be used to predict the expected quality of the QNN. Furthermore, we (ii) introduce new estimates for the expected accuracy of QNNs for moderately entangled training samples that are linearly dependent or orthogonal. Our analytical results are (iii) experimentally validated by simulating QNN training and analyzing the quality of the QNN after training.

arXiv:2309.13711•Quantum Machine Intelligence•Nov 4, 2025•4 citations

Quantum Neural Network and Its Application in Vehicle Classification

Shicai Yu, Ning Ma

Focusing on increase the capability of currency in the traffic net and decrease the possibility of loss on charge, in this paper, a novel method of vehicle classification by using quantum neural network (QNN) is proposed. A model of quantum neural network is proposed and its property is analyzed. The simulations show the proposed method can greatly reduce the training times also have enough accuracy. The method has efficiently trained the samples aggregate composed of some kinds of vehicle types, and completed the classification of vehicle.

International Conference on Natural Computation (ICNC)•Jan 1, 2008•14 citations

A Review of Quantum Neural Networks

Mohammad R. Khosravi, Maryam Zekri

•Dec 10, 2012•0 citations

Quantum neural networks (QNNs): inherently fuzzy feedforward neural networks

Gopathy Purushothaman, Nicolaos B. Karayiannis

This paper introduces quantum neural networks (QNNs), a class of feedforward neural networks which are inherently capable of estimating the structure of a feature space in the form of fuzzy membership information. The hidden units of these networks develop quantized representations of the crisp sample information provided by the training set in various graded levels of certainty. Experimental results show that QNNs have an inherent ability for recognizing structures in the feature space that conventional feedforward neural networks with sigmoidal hidden units lack.

IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks•Dec 23, 2002•151 citations

Simulations of quantum neural networks

Elizabeth Behrman, L.R. Nash, James E. Steck +2 more

Information Sciences•Oct 1, 2000•121 citations
Abstract Training classical neural networks generally requires a large number of training samples. Using entangled training samples, Quantum Neural Networks (QNNs) have the potential to significantly reduce the amount of training samples required in the training process. However, to minimize the number of incorrect predictions made by the resulting QNN, it is essential that the structure of the training samples meets certain requirements. On the one hand, the exact degree of entanglement must be fixed for the whole set of training samples. On the other hand, training samples must be linearly independent and non-orthogonal. However, how failing to meet these requirements affects the resulting QNN is not fully studied. To address this, we extend the proof of the Quantum No-Free-Lunch theorem to (i) provide a generalization of the theorem for varying degrees of entanglement. This generalization shows that the average degree of entanglement in the set of training samples can be used to predict the expected quality of the QNN. Furthermore, we (ii) introduce new estimates for the expected accuracy of QNNs for moderately entangled training samples that are linearly dependent or orthogonal. Our analytical results are (iii) experimentally validated by simulating QNN training and analyzing the quality of the QNN after training.
Focusing on increase the capability of currency in the traffic net and decrease the possibility of loss on charge, in this paper, a novel method of vehicle classification by using quantum neural network (QNN) is proposed. A model of quantum neural network is proposed and its property is analyzed. The simulations show the proposed method can greatly reduce the training times also have enough accuracy. The method has efficiently trained the samples aggregate composed of some kinds of vehicle types, and completed the classification of vehicle.
This paper introduces quantum neural networks (QNNs), a class of feedforward neural networks which are inherently capable of estimating the structure of a feature space in the form of fuzzy membership information. The hidden units of these networks develop quantized representations of the crisp sample information provided by the training set in various graded levels of certainty. Experimental results show that QNNs have an inherent ability for recognizing structures in the feature space that conventional feedforward neural networks with sigmoidal hidden units lack.