Matches in SemOpenAlex for { <https://semopenalex.org/work/W3185607546> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3185607546 endingPage "103346" @default.
- W3185607546 startingPage "103337" @default.
- W3185607546 abstract "Large machine learning models based on Convolutional Neural Networks (CNNs) with rapidly increasing number of parameters, trained with massive amounts of data, are being deployed in a wide array of computer vision tasks from self-driving cars to medical imaging. The insatiable demand for computing resources required to train these models is fast outpacing the advancement of classical computing hardware, and new frameworks including Optical Neural Networks (ONNs) and quantum computing are being explored as future alternatives. In this work, we report a novel quantum computing based deep learning model, the Quantum Optical Convolutional Neural Network (QOCNN), to alleviate the computational bottleneck in future computer vision applications. Using the popular MNIST dataset, we have benchmarked this new architecture against a traditional CNN based on the seminal LeNet model. We have also compared the performance with previously reported ONNs, namely the GridNet and ComplexNet, as well as a Quantum Optical Neural Network (QONN) that we built by combining the ComplexNet with quantum based sinusoidal nonlinearities. In essence, our work extends the prior research on QONN by adding quantum convolution and pooling layers preceding it. We have evaluated all the models by determining their accuracies, confusion matrices, Receiver Operating Characteristic (ROC) curves, and Matthews Correlation Coefficients. The performance of the models were similar overall, and the ROC curves indicated that the new QOCNN model is robust. Finally, we estimated the gains in computational efficiencies from executing this novel framework on a quantum computer. We conclude that switching to a quantum computing based approach to deep learning may result in comparable accuracies to classical models, while achieving unprecedented boosts in computational performances and drastic reduction in power consumption." @default.
- W3185607546 created "2021-08-02" @default.
- W3185607546 creator A5069299204 @default.
- W3185607546 creator A5081855394 @default.
- W3185607546 date "2021-01-01" @default.
- W3185607546 modified "2023-10-09" @default.
- W3185607546 title "Quantum Optical Convolutional Neural Network: A Novel Image Recognition Framework for Quantum Computing" @default.
- W3185607546 cites W2006290558 @default.
- W3185607546 cites W2042127289 @default.
- W3185607546 cites W2112796928 @default.
- W3185607546 cites W2559394418 @default.
- W3185607546 cites W2809254203 @default.
- W3185607546 cites W2887566712 @default.
- W3185607546 cites W2896712926 @default.
- W3185607546 cites W2904694042 @default.
- W3185607546 cites W2935480346 @default.
- W3185607546 cites W2963173679 @default.
- W3185607546 cites W2975429865 @default.
- W3185607546 cites W3004965358 @default.
- W3185607546 cites W3098290163 @default.
- W3185607546 cites W3111297213 @default.
- W3185607546 doi "https://doi.org/10.1109/access.2021.3098775" @default.
- W3185607546 hasPublicationYear "2021" @default.
- W3185607546 type Work @default.
- W3185607546 sameAs 3185607546 @default.
- W3185607546 citedByCount "13" @default.
- W3185607546 countsByYear W31856075462021 @default.
- W3185607546 countsByYear W31856075462022 @default.
- W3185607546 countsByYear W31856075462023 @default.
- W3185607546 crossrefType "journal-article" @default.
- W3185607546 hasAuthorship W3185607546A5069299204 @default.
- W3185607546 hasAuthorship W3185607546A5081855394 @default.
- W3185607546 hasBestOaLocation W31856075461 @default.
- W3185607546 hasConcept C108583219 @default.
- W3185607546 hasConcept C113775141 @default.
- W3185607546 hasConcept C121332964 @default.
- W3185607546 hasConcept C149635348 @default.
- W3185607546 hasConcept C154945302 @default.
- W3185607546 hasConcept C190502265 @default.
- W3185607546 hasConcept C2780513914 @default.
- W3185607546 hasConcept C41008148 @default.
- W3185607546 hasConcept C50644808 @default.
- W3185607546 hasConcept C58053490 @default.
- W3185607546 hasConcept C62520636 @default.
- W3185607546 hasConcept C81363708 @default.
- W3185607546 hasConcept C84114770 @default.
- W3185607546 hasConceptScore W3185607546C108583219 @default.
- W3185607546 hasConceptScore W3185607546C113775141 @default.
- W3185607546 hasConceptScore W3185607546C121332964 @default.
- W3185607546 hasConceptScore W3185607546C149635348 @default.
- W3185607546 hasConceptScore W3185607546C154945302 @default.
- W3185607546 hasConceptScore W3185607546C190502265 @default.
- W3185607546 hasConceptScore W3185607546C2780513914 @default.
- W3185607546 hasConceptScore W3185607546C41008148 @default.
- W3185607546 hasConceptScore W3185607546C50644808 @default.
- W3185607546 hasConceptScore W3185607546C58053490 @default.
- W3185607546 hasConceptScore W3185607546C62520636 @default.
- W3185607546 hasConceptScore W3185607546C81363708 @default.
- W3185607546 hasConceptScore W3185607546C84114770 @default.
- W3185607546 hasLocation W31856075461 @default.
- W3185607546 hasLocation W31856075462 @default.
- W3185607546 hasOpenAccess W3185607546 @default.
- W3185607546 hasPrimaryLocation W31856075461 @default.
- W3185607546 hasRelatedWork W2167735388 @default.
- W3185607546 hasRelatedWork W2285788670 @default.
- W3185607546 hasRelatedWork W2731899572 @default.
- W3185607546 hasRelatedWork W2947175736 @default.
- W3185607546 hasRelatedWork W3133861977 @default.
- W3185607546 hasRelatedWork W3156786002 @default.
- W3185607546 hasRelatedWork W4309224979 @default.
- W3185607546 hasRelatedWork W4312417841 @default.
- W3185607546 hasRelatedWork W4317374280 @default.
- W3185607546 hasRelatedWork W4321369474 @default.
- W3185607546 hasVolume "9" @default.
- W3185607546 isParatext "false" @default.
- W3185607546 isRetracted "false" @default.
- W3185607546 magId "3185607546" @default.
- W3185607546 workType "article" @default.