Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387623795> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4387623795 endingPage "1" @default.
- W4387623795 startingPage "1" @default.
- W4387623795 abstract "Memristive crossbar arrays have gained considerable attention from researchers to perform analog in-memory vector-matrix multiplications in machine learning accelerators with low power and constant computational time. This work introduces a comprehensive framework for co-designing the software and hardware for deep neural networks (DNN) based on memristive and memcapacitive crossbars while considering various non-idealities. The model takes into account device-level factors, including conductance variation, cycle-to-cycle variation, device-to-device variation, peripheral circuits for error/weight gradient computation, and high tolerance. The overall neural network performance is thoroughly assessed by integrating these elements into a unified DNN training process. The proposed framework is implemented using a hybrid approach with Python and PyTorch. Performance evaluation was conducted using a simplified 8-layer VGG network on a measured 128×128 array with weight resolution. Remarkably, the memristive and memcapacitive crossbar arrays achieved outstanding training accuracies of 90.02% and 91.03%, respectively, for the CIFAR-10 dataset. Additionally, detailed hardware estimation for both mem-elements devices is provided, enabling meaningful comparisons with prior works." @default.
- W4387623795 created "2023-10-14" @default.
- W4387623795 creator A5036000098 @default.
- W4387623795 creator A5070658985 @default.
- W4387623795 date "2023-01-01" @default.
- W4387623795 modified "2023-10-15" @default.
- W4387623795 title "Framework for In-memory Computing based on Memristor and Memcapacitor for On-Chip Training" @default.
- W4387623795 doi "https://doi.org/10.1109/access.2023.3324375" @default.
- W4387623795 hasPublicationYear "2023" @default.
- W4387623795 type Work @default.
- W4387623795 citedByCount "0" @default.
- W4387623795 crossrefType "journal-article" @default.
- W4387623795 hasAuthorship W4387623795A5036000098 @default.
- W4387623795 hasAuthorship W4387623795A5070658985 @default.
- W4387623795 hasBestOaLocation W43876237951 @default.
- W4387623795 hasConcept C108583219 @default.
- W4387623795 hasConcept C111919701 @default.
- W4387623795 hasConcept C113775141 @default.
- W4387623795 hasConcept C11413529 @default.
- W4387623795 hasConcept C118524514 @default.
- W4387623795 hasConcept C119599485 @default.
- W4387623795 hasConcept C127413603 @default.
- W4387623795 hasConcept C150072547 @default.
- W4387623795 hasConcept C154945302 @default.
- W4387623795 hasConcept C165801399 @default.
- W4387623795 hasConcept C182019814 @default.
- W4387623795 hasConcept C190502265 @default.
- W4387623795 hasConcept C199360897 @default.
- W4387623795 hasConcept C24326235 @default.
- W4387623795 hasConcept C2777904410 @default.
- W4387623795 hasConcept C29984679 @default.
- W4387623795 hasConcept C41008148 @default.
- W4387623795 hasConcept C45374587 @default.
- W4387623795 hasConcept C50644808 @default.
- W4387623795 hasConcept C519991488 @default.
- W4387623795 hasConcept C76155785 @default.
- W4387623795 hasConcept C93389723 @default.
- W4387623795 hasConcept C98045186 @default.
- W4387623795 hasConceptScore W4387623795C108583219 @default.
- W4387623795 hasConceptScore W4387623795C111919701 @default.
- W4387623795 hasConceptScore W4387623795C113775141 @default.
- W4387623795 hasConceptScore W4387623795C11413529 @default.
- W4387623795 hasConceptScore W4387623795C118524514 @default.
- W4387623795 hasConceptScore W4387623795C119599485 @default.
- W4387623795 hasConceptScore W4387623795C127413603 @default.
- W4387623795 hasConceptScore W4387623795C150072547 @default.
- W4387623795 hasConceptScore W4387623795C154945302 @default.
- W4387623795 hasConceptScore W4387623795C165801399 @default.
- W4387623795 hasConceptScore W4387623795C182019814 @default.
- W4387623795 hasConceptScore W4387623795C190502265 @default.
- W4387623795 hasConceptScore W4387623795C199360897 @default.
- W4387623795 hasConceptScore W4387623795C24326235 @default.
- W4387623795 hasConceptScore W4387623795C2777904410 @default.
- W4387623795 hasConceptScore W4387623795C29984679 @default.
- W4387623795 hasConceptScore W4387623795C41008148 @default.
- W4387623795 hasConceptScore W4387623795C45374587 @default.
- W4387623795 hasConceptScore W4387623795C50644808 @default.
- W4387623795 hasConceptScore W4387623795C519991488 @default.
- W4387623795 hasConceptScore W4387623795C76155785 @default.
- W4387623795 hasConceptScore W4387623795C93389723 @default.
- W4387623795 hasConceptScore W4387623795C98045186 @default.
- W4387623795 hasFunder F4320322120 @default.
- W4387623795 hasLocation W43876237951 @default.
- W4387623795 hasOpenAccess W4387623795 @default.
- W4387623795 hasPrimaryLocation W43876237951 @default.
- W4387623795 hasRelatedWork W2005875039 @default.
- W4387623795 hasRelatedWork W2015477599 @default.
- W4387623795 hasRelatedWork W2015497999 @default.
- W4387623795 hasRelatedWork W2144085790 @default.
- W4387623795 hasRelatedWork W2171130799 @default.
- W4387623795 hasRelatedWork W2548135880 @default.
- W4387623795 hasRelatedWork W3005999147 @default.
- W4387623795 hasRelatedWork W3176428941 @default.
- W4387623795 hasRelatedWork W3177379469 @default.
- W4387623795 hasRelatedWork W4386216112 @default.
- W4387623795 isParatext "false" @default.
- W4387623795 isRetracted "false" @default.
- W4387623795 workType "article" @default.