Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090344218> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W3090344218 abstract "The operation of stochastic neural networks with randomly disconnected or blanked out synaptic connections can optimize the power consumption of its circuit implementations in traditional crossbars. However, the permanent disconnection of some synaptic weights can lead to the poor performance of the network, which will require further optimization of the remaining active synapses. In this work, we propose a learning scheme for such stochastically blanked out neural networks. The architecture of the neural network is implemented with standard 0.18u CMOS circuits, in 1T1M crossbar configuration for controlling the blank out rate. The results of the retraining the network with up to 50% of disconnected synapses are reported for the standard image classification problem such as MNIST handwritten digits recognition." @default.
- W3090344218 created "2020-10-08" @default.
- W3090344218 creator A5001019582 @default.
- W3090344218 creator A5017719665 @default.
- W3090344218 creator A5060736222 @default.
- W3090344218 date "2020-10-01" @default.
- W3090344218 modified "2023-09-27" @default.
- W3090344218 title "Self Tuning Stochastic Weighted Neural Networks" @default.
- W3090344218 cites W1976342705 @default.
- W3090344218 cites W2013700857 @default.
- W3090344218 cites W2623410569 @default.
- W3090344218 cites W2883149906 @default.
- W3090344218 cites W2910506572 @default.
- W3090344218 cites W2940297489 @default.
- W3090344218 cites W2946591837 @default.
- W3090344218 doi "https://doi.org/10.1109/iscas45731.2020.9180809" @default.
- W3090344218 hasPublicationYear "2020" @default.
- W3090344218 type Work @default.
- W3090344218 sameAs 3090344218 @default.
- W3090344218 citedByCount "1" @default.
- W3090344218 countsByYear W30903442182022 @default.
- W3090344218 crossrefType "proceedings-article" @default.
- W3090344218 hasAuthorship W3090344218A5001019582 @default.
- W3090344218 hasAuthorship W3090344218A5017719665 @default.
- W3090344218 hasAuthorship W3090344218A5060736222 @default.
- W3090344218 hasConcept C105795698 @default.
- W3090344218 hasConcept C147168706 @default.
- W3090344218 hasConcept C154945302 @default.
- W3090344218 hasConcept C33923547 @default.
- W3090344218 hasConcept C41008148 @default.
- W3090344218 hasConcept C50644808 @default.
- W3090344218 hasConcept C8272713 @default.
- W3090344218 hasConcept C86582703 @default.
- W3090344218 hasConceptScore W3090344218C105795698 @default.
- W3090344218 hasConceptScore W3090344218C147168706 @default.
- W3090344218 hasConceptScore W3090344218C154945302 @default.
- W3090344218 hasConceptScore W3090344218C33923547 @default.
- W3090344218 hasConceptScore W3090344218C41008148 @default.
- W3090344218 hasConceptScore W3090344218C50644808 @default.
- W3090344218 hasConceptScore W3090344218C8272713 @default.
- W3090344218 hasConceptScore W3090344218C86582703 @default.
- W3090344218 hasLocation W30903442181 @default.
- W3090344218 hasOpenAccess W3090344218 @default.
- W3090344218 hasPrimaryLocation W30903442181 @default.
- W3090344218 hasRelatedWork W1544020935 @default.
- W3090344218 hasRelatedWork W1592089735 @default.
- W3090344218 hasRelatedWork W1975147165 @default.
- W3090344218 hasRelatedWork W2110051564 @default.
- W3090344218 hasRelatedWork W2148454247 @default.
- W3090344218 hasRelatedWork W2378845890 @default.
- W3090344218 hasRelatedWork W2386387936 @default.
- W3090344218 hasRelatedWork W2581796212 @default.
- W3090344218 hasRelatedWork W2627078154 @default.
- W3090344218 hasRelatedWork W3199255997 @default.
- W3090344218 isParatext "false" @default.
- W3090344218 isRetracted "false" @default.
- W3090344218 magId "3090344218" @default.
- W3090344218 workType "article" @default.