Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037924448> ?p ?o ?g. }
- W3037924448 abstract "Recurrent neural networks are the foundation of many sequence-to-sequence models in machine learning, such as machine translation and speech synthesis. In contrast, applied quantum computing is in its infancy. Nevertheless there already exist quantum machine learning models such as variational quantum eigensolvers which have been used successfully e.g. in the context of energy minimization tasks. In this work we construct a quantum recurrent neural network (QRNN) with demonstrable performance on non-trivial tasks such as sequence learning and integer digit classification. The QRNN cell is built from parametrized quantum neurons, which, in conjunction with amplitude amplification, create a nonlinear activation of polynomials of its inputs and cell state, and allow the extraction of a probability distribution over predicted classes at each step. To study the model's performance, we provide an implementation in pytorch, which allows the relatively efficient optimization of parametrized quantum circuits with thousands of parameters. We establish a QRNN training setup by benchmarking optimization hyperparameters, and analyse suitable network topologies for simple memorisation and sequence prediction tasks from Elman's seminal paper (1990) on temporal structure learning. We then proceed to evaluate the QRNN on MNIST classification, both by feeding the QRNN each image pixel-by-pixel; and by utilising modern data augmentation as preprocessing step. Finally, we analyse to what extent the unitary nature of the network counteracts the vanishing gradient problem that plagues many existing quantum classifiers and classical RNNs." @default.
- W3037924448 created "2020-07-02" @default.
- W3037924448 creator A5000073123 @default.
- W3037924448 date "2020-06-25" @default.
- W3037924448 modified "2023-10-15" @default.
- W3037924448 title "Recurrent Quantum Neural Networks" @default.
- W3037924448 cites W1492999010 @default.
- W3037924448 cites W2110485445 @default.
- W3037924448 cites W2133963973 @default.
- W3037924448 cites W2141058327 @default.
- W3037924448 cites W2161685427 @default.
- W3037924448 cites W2170807564 @default.
- W3037924448 cites W2187089797 @default.
- W3037924448 cites W2257937122 @default.
- W3037924448 cites W2402302915 @default.
- W3037924448 cites W2547718140 @default.
- W3037924448 cites W2626194254 @default.
- W3037924448 cites W2772274464 @default.
- W3037924448 cites W2786167326 @default.
- W3037924448 cites W2786672974 @default.
- W3037924448 cites W2788800397 @default.
- W3037924448 cites W2788945937 @default.
- W3037924448 cites W2798702047 @default.
- W3037924448 cites W2804076222 @default.
- W3037924448 cites W2923481626 @default.
- W3037924448 cites W2946683488 @default.
- W3037924448 cites W2962930448 @default.
- W3037924448 cites W2963042606 @default.
- W3037924448 cites W2963088785 @default.
- W3037924448 cites W2964110616 @default.
- W3037924448 cites W2964304579 @default.
- W3037924448 cites W2976350580 @default.
- W3037924448 cites W2994673210 @default.
- W3037924448 cites W2995057155 @default.
- W3037924448 cites W3098445865 @default.
- W3037924448 cites W3100806676 @default.
- W3037924448 cites W3101135395 @default.
- W3037924448 cites W3157156950 @default.
- W3037924448 hasPublicationYear "2020" @default.
- W3037924448 type Work @default.
- W3037924448 sameAs 3037924448 @default.
- W3037924448 citedByCount "7" @default.
- W3037924448 countsByYear W30379244482021 @default.
- W3037924448 crossrefType "posted-content" @default.
- W3037924448 hasAuthorship W3037924448A5000073123 @default.
- W3037924448 hasConcept C11413529 @default.
- W3037924448 hasConcept C119857082 @default.
- W3037924448 hasConcept C121332964 @default.
- W3037924448 hasConcept C147168706 @default.
- W3037924448 hasConcept C151730666 @default.
- W3037924448 hasConcept C154945302 @default.
- W3037924448 hasConcept C190502265 @default.
- W3037924448 hasConcept C2778112365 @default.
- W3037924448 hasConcept C2779094486 @default.
- W3037924448 hasConcept C2779343474 @default.
- W3037924448 hasConcept C40506919 @default.
- W3037924448 hasConcept C41008148 @default.
- W3037924448 hasConcept C50644808 @default.
- W3037924448 hasConcept C54355233 @default.
- W3037924448 hasConcept C58053490 @default.
- W3037924448 hasConcept C62520636 @default.
- W3037924448 hasConcept C84114770 @default.
- W3037924448 hasConcept C86803240 @default.
- W3037924448 hasConcept C97541855 @default.
- W3037924448 hasConceptScore W3037924448C11413529 @default.
- W3037924448 hasConceptScore W3037924448C119857082 @default.
- W3037924448 hasConceptScore W3037924448C121332964 @default.
- W3037924448 hasConceptScore W3037924448C147168706 @default.
- W3037924448 hasConceptScore W3037924448C151730666 @default.
- W3037924448 hasConceptScore W3037924448C154945302 @default.
- W3037924448 hasConceptScore W3037924448C190502265 @default.
- W3037924448 hasConceptScore W3037924448C2778112365 @default.
- W3037924448 hasConceptScore W3037924448C2779094486 @default.
- W3037924448 hasConceptScore W3037924448C2779343474 @default.
- W3037924448 hasConceptScore W3037924448C40506919 @default.
- W3037924448 hasConceptScore W3037924448C41008148 @default.
- W3037924448 hasConceptScore W3037924448C50644808 @default.
- W3037924448 hasConceptScore W3037924448C54355233 @default.
- W3037924448 hasConceptScore W3037924448C58053490 @default.
- W3037924448 hasConceptScore W3037924448C62520636 @default.
- W3037924448 hasConceptScore W3037924448C84114770 @default.
- W3037924448 hasConceptScore W3037924448C86803240 @default.
- W3037924448 hasConceptScore W3037924448C97541855 @default.
- W3037924448 hasLocation W30379244481 @default.
- W3037924448 hasOpenAccess W3037924448 @default.
- W3037924448 hasPrimaryLocation W30379244481 @default.
- W3037924448 hasRelatedWork W1568345435 @default.
- W3037924448 hasRelatedWork W1631356911 @default.
- W3037924448 hasRelatedWork W1988369744 @default.
- W3037924448 hasRelatedWork W2161685427 @default.
- W3037924448 hasRelatedWork W2559394418 @default.
- W3037924448 hasRelatedWork W2754797405 @default.
- W3037924448 hasRelatedWork W2781738013 @default.
- W3037924448 hasRelatedWork W2788945937 @default.
- W3037924448 hasRelatedWork W2790388700 @default.
- W3037924448 hasRelatedWork W2796293949 @default.
- W3037924448 hasRelatedWork W2798967590 @default.
- W3037924448 hasRelatedWork W2896712926 @default.
- W3037924448 hasRelatedWork W2901859177 @default.
- W3037924448 hasRelatedWork W2903221501 @default.