FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2020105341> ?p ?o ?g. }

• W2020105341 endingPage "e112659" @default.
• W2020105341 startingPage "e112659" @default.
• W2020105341 abstract "To realize an analog artificial neural network hardware, the circuit element for synapse function is important because the number of synapse elements is much larger than that of neuron elements. One of the candidates for this synapse element is a ferroelectric memristor. This device functions as a voltage controllable variable resistor, which can be applied to a synapse weight. However, its conductance shows hysteresis characteristics and dispersion to the input voltage. Therefore, the conductance values vary according to the history of the height and the width of the applied pulse voltage. Due to the difficulty of controlling the accurate conductance, it is not easy to apply the back-propagation learning algorithm to the neural network hardware having memristor synapses. To solve this problem, we proposed and simulated a learning operation procedure as follows. Employing a weight perturbation technique, we derived the error change. When the error reduced, the next pulse voltage was updated according to the back-propagation learning algorithm. If the error increased the amplitude of the next voltage pulse was set in such way as to cause similar memristor conductance but in the opposite voltage scanning direction. By this operation, we could eliminate the hysteresis and confirmed that the simulation of the learning operation converged. We also adopted conductance dispersion numerically in the simulation. We examined the probability that the error decreased to a designated value within a predetermined loop number. The ferroelectric has the characteristics that the magnitude of polarization does not become smaller when voltages having the same polarity are applied. These characteristics greatly improved the probability even if the learning rate was small, if the magnitude of the dispersion is adequate. Because the dispersion of analog circuit elements is inevitable, this learning operation procedure is useful for analog neural network hardware." @default.
• W2020105341 created "2016-06-24" @default.
• W2020105341 creator A5010865972 @default.
• W2020105341 creator A5050906876 @default.
• W2020105341 creator A5075410901 @default.
• W2020105341 creator A5078215874 @default.
• W2020105341 date "2014-11-13" @default.
• W2020105341 modified "2023-09-25" @default.
• W2020105341 title "Back-Propagation Operation for Analog Neural Network Hardware with Synapse Components Having Hysteresis Characteristics" @default.
• W2020105341 cites W1964773927 @default.
• W2020105341 cites W1968288892 @default.
• W2020105341 cites W1979404250 @default.
• W2020105341 cites W1980390679 @default.
• W2020105341 cites W1993472407 @default.
• W2020105341 cites W2000814332 @default.
• W2020105341 cites W2007656487 @default.
• W2020105341 cites W2016922062 @default.
• W2020105341 cites W2021383442 @default.
• W2020105341 cites W2077895767 @default.
• W2020105341 cites W2098437527 @default.
• W2020105341 cites W2112181056 @default.
• W2020105341 cites W2136288682 @default.
• W2020105341 cites W2136922672 @default.
• W2020105341 cites W2148251150 @default.
• W2020105341 cites W2155954834 @default.
• W2020105341 cites W2156084351 @default.
• W2020105341 cites W2164025094 @default.
• W2020105341 cites W2334364695 @default.
• W2020105341 cites W2545004311 @default.
• W2020105341 doi "https://doi.org/10.1371/journal.pone.0112659" @default.
• W2020105341 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/4231062" @default.
• W2020105341 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25393715" @default.
• W2020105341 hasPublicationYear "2014" @default.
• W2020105341 type Work @default.
• W2020105341 sameAs 2020105341 @default.
• W2020105341 citedByCount "7" @default.
• W2020105341 countsByYear W20201053412016 @default.
• W2020105341 countsByYear W20201053412017 @default.
• W2020105341 countsByYear W20201053412018 @default.
• W2020105341 countsByYear W20201053412019 @default.
• W2020105341 countsByYear W20201053412021 @default.
• W2020105341 countsByYear W20201053412022 @default.
• W2020105341 countsByYear W20201053412023 @default.
• W2020105341 crossrefType "journal-article" @default.
• W2020105341 hasAuthorship W2020105341A5010865972 @default.
• W2020105341 hasAuthorship W2020105341A5050906876 @default.
• W2020105341 hasAuthorship W2020105341A5075410901 @default.
• W2020105341 hasAuthorship W2020105341A5078215874 @default.
• W2020105341 hasBestOaLocation W20201053411 @default.
• W2020105341 hasConcept C11413529 @default.
• W2020105341 hasConcept C119599485 @default.
• W2020105341 hasConcept C121332964 @default.
• W2020105341 hasConcept C121932024 @default.
• W2020105341 hasConcept C127413603 @default.
• W2020105341 hasConcept C137488568 @default.
• W2020105341 hasConcept C150072547 @default.
• W2020105341 hasConcept C154945302 @default.
• W2020105341 hasConcept C165801399 @default.
• W2020105341 hasConcept C184720557 @default.
• W2020105341 hasConcept C192562407 @default.
• W2020105341 hasConcept C24326235 @default.
• W2020105341 hasConcept C26873012 @default.
• W2020105341 hasConcept C2775924081 @default.
• W2020105341 hasConcept C41008148 @default.
• W2020105341 hasConcept C47446073 @default.
• W2020105341 hasConcept C50644808 @default.
• W2020105341 hasConcept C66949984 @default.
• W2020105341 hasConceptScore W2020105341C11413529 @default.
• W2020105341 hasConceptScore W2020105341C119599485 @default.
• W2020105341 hasConceptScore W2020105341C121332964 @default.
• W2020105341 hasConceptScore W2020105341C121932024 @default.
• W2020105341 hasConceptScore W2020105341C127413603 @default.
• W2020105341 hasConceptScore W2020105341C137488568 @default.
• W2020105341 hasConceptScore W2020105341C150072547 @default.
• W2020105341 hasConceptScore W2020105341C154945302 @default.
• W2020105341 hasConceptScore W2020105341C165801399 @default.
• W2020105341 hasConceptScore W2020105341C184720557 @default.
• W2020105341 hasConceptScore W2020105341C192562407 @default.
• W2020105341 hasConceptScore W2020105341C24326235 @default.
• W2020105341 hasConceptScore W2020105341C26873012 @default.
• W2020105341 hasConceptScore W2020105341C2775924081 @default.
• W2020105341 hasConceptScore W2020105341C41008148 @default.
• W2020105341 hasConceptScore W2020105341C47446073 @default.
• W2020105341 hasConceptScore W2020105341C50644808 @default.
• W2020105341 hasConceptScore W2020105341C66949984 @default.
• W2020105341 hasIssue "11" @default.
• W2020105341 hasLocation W20201053411 @default.
• W2020105341 hasLocation W20201053412 @default.
• W2020105341 hasLocation W20201053413 @default.
• W2020105341 hasLocation W20201053414 @default.
• W2020105341 hasLocation W20201053415 @default.
• W2020105341 hasOpenAccess W2020105341 @default.
• W2020105341 hasPrimaryLocation W20201053411 @default.
• W2020105341 hasRelatedWork W1928989178 @default.
• W2020105341 hasRelatedWork W1967864158 @default.
• W2020105341 hasRelatedWork W2076948725 @default.
• W2020105341 hasRelatedWork W2154880818 @default.
• W2020105341 hasRelatedWork W2341458164 @default.

• next