Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385267257> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4385267257 endingPage "1" @default.
- W4385267257 startingPage "1" @default.
- W4385267257 abstract "As neural network models are developed and optimized, the use of neural networks in edge devices is increasing, where low-bit neural networks, such as binary neural networks and mixed-precision neural networks, are ideal for edge AI applications. Peripheral circuits and in-memory computing macro are the main components for deploying low-bit precision neural networks on edge AI. However, existing peripheral circuits, including communication units, control modules and analog-to-digital converters (ADCs), are implemented by software or mixed-signal circuits, resulting in significant power and area overheads. To address this issue, memristor-based reconfigurable circuits are proposed for a fully analog implementation of low-bit neural networks without ADCs. In addition, a memristor-based mixed-precision network with a variety of mixed-precision modes is illustrated to verify the effectiveness of deploying low-bit neural networks on edge devices based on the proposed circuits. Furthermore, hybrid simulation results demonstrate that the proposed memristor-based mixed-precision network achieves 84.8 87.5% accuracy on the CIFAR-10 dataset, and the parameter scale of the network model is reduced by 1.6 20x. The circuit analysis demonstrated that the proposed circuits are accurate, robust, and energy-efficient with varying mixed precision, providing a promising and universal solution for applying low-bit neural networks on edge devices." @default.
- W4385267257 created "2023-07-27" @default.
- W4385267257 creator A5032754937 @default.
- W4385267257 creator A5034322739 @default.
- W4385267257 creator A5035048973 @default.
- W4385267257 creator A5058073627 @default.
- W4385267257 creator A5074904368 @default.
- W4385267257 creator A5087454088 @default.
- W4385267257 date "2023-01-01" @default.
- W4385267257 modified "2023-10-12" @default.
- W4385267257 title "Efficient Low-Bit Neural Network With Memristor-Based Reconfigurable Circuits" @default.
- W4385267257 doi "https://doi.org/10.1109/tcsii.2023.3298910" @default.
- W4385267257 hasPublicationYear "2023" @default.
- W4385267257 type Work @default.
- W4385267257 citedByCount "0" @default.
- W4385267257 crossrefType "journal-article" @default.
- W4385267257 hasAuthorship W4385267257A5032754937 @default.
- W4385267257 hasAuthorship W4385267257A5034322739 @default.
- W4385267257 hasAuthorship W4385267257A5035048973 @default.
- W4385267257 hasAuthorship W4385267257A5058073627 @default.
- W4385267257 hasAuthorship W4385267257A5074904368 @default.
- W4385267257 hasAuthorship W4385267257A5087454088 @default.
- W4385267257 hasConcept C118403218 @default.
- W4385267257 hasConcept C119599485 @default.
- W4385267257 hasConcept C119857082 @default.
- W4385267257 hasConcept C127413603 @default.
- W4385267257 hasConcept C134146338 @default.
- W4385267257 hasConcept C150072547 @default.
- W4385267257 hasConcept C154945302 @default.
- W4385267257 hasConcept C162307627 @default.
- W4385267257 hasConcept C24326235 @default.
- W4385267257 hasConcept C41008148 @default.
- W4385267257 hasConcept C50644808 @default.
- W4385267257 hasConcept C81843906 @default.
- W4385267257 hasConcept C9390403 @default.
- W4385267257 hasConceptScore W4385267257C118403218 @default.
- W4385267257 hasConceptScore W4385267257C119599485 @default.
- W4385267257 hasConceptScore W4385267257C119857082 @default.
- W4385267257 hasConceptScore W4385267257C127413603 @default.
- W4385267257 hasConceptScore W4385267257C134146338 @default.
- W4385267257 hasConceptScore W4385267257C150072547 @default.
- W4385267257 hasConceptScore W4385267257C154945302 @default.
- W4385267257 hasConceptScore W4385267257C162307627 @default.
- W4385267257 hasConceptScore W4385267257C24326235 @default.
- W4385267257 hasConceptScore W4385267257C41008148 @default.
- W4385267257 hasConceptScore W4385267257C50644808 @default.
- W4385267257 hasConceptScore W4385267257C81843906 @default.
- W4385267257 hasConceptScore W4385267257C9390403 @default.
- W4385267257 hasFunder F4320321001 @default.
- W4385267257 hasFunder F4320335787 @default.
- W4385267257 hasLocation W43852672571 @default.
- W4385267257 hasOpenAccess W4385267257 @default.
- W4385267257 hasPrimaryLocation W43852672571 @default.
- W4385267257 hasRelatedWork W2268772050 @default.
- W4385267257 hasRelatedWork W2273072955 @default.
- W4385267257 hasRelatedWork W2547075610 @default.
- W4385267257 hasRelatedWork W2612923708 @default.
- W4385267257 hasRelatedWork W3014780561 @default.
- W4385267257 hasRelatedWork W3042287383 @default.
- W4385267257 hasRelatedWork W3082198935 @default.
- W4385267257 hasRelatedWork W3082575083 @default.
- W4385267257 hasRelatedWork W3143082377 @default.
- W4385267257 hasRelatedWork W4317665987 @default.
- W4385267257 isParatext "false" @default.
- W4385267257 isRetracted "false" @default.
- W4385267257 workType "article" @default.