Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387389627> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4387389627 abstract "Quantum Neural Networks (QNNs) are suggested as one of the quantum algorithms which can be efficiently simulated with a low depth on near-term quantum hardware in the presence of noises. However, their performance highly relies on choosing the most suitable architecture of Variational Quantum Algorithms (VQAs), and the problem-agnostic models often suffer issues regarding trainability and generalization power. As a solution, the most recent works explore Geometric Quantum Machine Learning (GQML) using QNNs equivariant with respect to the underlying symmetry of the dataset. GQML adds an inductive bias to the model by incorporating the prior knowledge on the given dataset and leads to enhancing the optimization performance while constraining the search space. This work proposes equivariant Quantum Convolutional Neural Networks (EquivQCNNs) for image classification under planar $p4m$ symmetry, including reflectional and $90^circ$ rotational symmetry. We present the results tested in different use cases, such as phase detection of the 2D Ising model and classification of the extended MNIST dataset, and compare them with those obtained with the non-equivariant model, proving that the equivariance fosters better generalization of the model." @default.
- W4387389627 created "2023-10-06" @default.
- W4387389627 creator A5001923006 @default.
- W4387389627 creator A5017741513 @default.
- W4387389627 creator A5067965505 @default.
- W4387389627 creator A5077967889 @default.
- W4387389627 date "2023-10-03" @default.
- W4387389627 modified "2023-10-07" @default.
- W4387389627 title "Approximately Equivariant Quantum Neural Network for $p4m$ Group Symmetries in Images" @default.
- W4387389627 doi "https://doi.org/10.48550/arxiv.2310.02323" @default.
- W4387389627 hasPublicationYear "2023" @default.
- W4387389627 type Work @default.
- W4387389627 citedByCount "0" @default.
- W4387389627 crossrefType "posted-content" @default.
- W4387389627 hasAuthorship W4387389627A5001923006 @default.
- W4387389627 hasAuthorship W4387389627A5017741513 @default.
- W4387389627 hasAuthorship W4387389627A5067965505 @default.
- W4387389627 hasAuthorship W4387389627A5077967889 @default.
- W4387389627 hasBestOaLocation W43873896271 @default.
- W4387389627 hasConcept C11413529 @default.
- W4387389627 hasConcept C114614502 @default.
- W4387389627 hasConcept C121332964 @default.
- W4387389627 hasConcept C121864883 @default.
- W4387389627 hasConcept C134306372 @default.
- W4387389627 hasConcept C154945302 @default.
- W4387389627 hasConcept C171036898 @default.
- W4387389627 hasConcept C177148314 @default.
- W4387389627 hasConcept C184720557 @default.
- W4387389627 hasConcept C190502265 @default.
- W4387389627 hasConcept C202444582 @default.
- W4387389627 hasConcept C2524010 @default.
- W4387389627 hasConcept C2779886137 @default.
- W4387389627 hasConcept C33923547 @default.
- W4387389627 hasConcept C41008148 @default.
- W4387389627 hasConcept C50644808 @default.
- W4387389627 hasConcept C51329190 @default.
- W4387389627 hasConcept C62520636 @default.
- W4387389627 hasConcept C81363708 @default.
- W4387389627 hasConcept C84114770 @default.
- W4387389627 hasConcept C96469262 @default.
- W4387389627 hasConceptScore W4387389627C11413529 @default.
- W4387389627 hasConceptScore W4387389627C114614502 @default.
- W4387389627 hasConceptScore W4387389627C121332964 @default.
- W4387389627 hasConceptScore W4387389627C121864883 @default.
- W4387389627 hasConceptScore W4387389627C134306372 @default.
- W4387389627 hasConceptScore W4387389627C154945302 @default.
- W4387389627 hasConceptScore W4387389627C171036898 @default.
- W4387389627 hasConceptScore W4387389627C177148314 @default.
- W4387389627 hasConceptScore W4387389627C184720557 @default.
- W4387389627 hasConceptScore W4387389627C190502265 @default.
- W4387389627 hasConceptScore W4387389627C202444582 @default.
- W4387389627 hasConceptScore W4387389627C2524010 @default.
- W4387389627 hasConceptScore W4387389627C2779886137 @default.
- W4387389627 hasConceptScore W4387389627C33923547 @default.
- W4387389627 hasConceptScore W4387389627C41008148 @default.
- W4387389627 hasConceptScore W4387389627C50644808 @default.
- W4387389627 hasConceptScore W4387389627C51329190 @default.
- W4387389627 hasConceptScore W4387389627C62520636 @default.
- W4387389627 hasConceptScore W4387389627C81363708 @default.
- W4387389627 hasConceptScore W4387389627C84114770 @default.
- W4387389627 hasConceptScore W4387389627C96469262 @default.
- W4387389627 hasLocation W43873896271 @default.
- W4387389627 hasOpenAccess W4387389627 @default.
- W4387389627 hasPrimaryLocation W43873896271 @default.
- W4387389627 hasRelatedWork W2069360731 @default.
- W4387389627 hasRelatedWork W2263923500 @default.
- W4387389627 hasRelatedWork W2392521623 @default.
- W4387389627 hasRelatedWork W2734358244 @default.
- W4387389627 hasRelatedWork W2770089535 @default.
- W4387389627 hasRelatedWork W2886711096 @default.
- W4387389627 hasRelatedWork W2950475743 @default.
- W4387389627 hasRelatedWork W3155941649 @default.
- W4387389627 hasRelatedWork W4380078352 @default.
- W4387389627 hasRelatedWork W4386603768 @default.
- W4387389627 isParatext "false" @default.
- W4387389627 isRetracted "false" @default.
- W4387389627 workType "article" @default.