Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980456984> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2980456984 abstract "Recent years have seen marked developments in deep neural networks (DNNs) stemming from advances in hardware and increasingly large datasets. DNNs are now routinely used in domains including computer vision and language processing. At their core, DNNs rely heavily on multiply-accumulate (MAC) operations making them well-suited for the highly parallel computational abilities of GPUs. GPUs, however, are von Neumann in architecture and physically separate memory blocks from computational blocks. This exacts an unavoidable time and energy cost associated with data transport known as the von-Neumann bottleneck. While incremental advances in digital hardware accelerators mitigating the von Neumann bottleneck will continue, we explore the potentially game-changing advantages of non-von Neumann architectures that perform MAC operations within the memory. This is achieved using a crossbar array of analog memory as shown in Fig. 1, which serves as the basis of our analog DNN hardware accelerators, and is amenable to both DNN training and forward inference [1], [2]. Recent work from our group has shown analog DNN hardware accelerators capable of 280× speedup in per area throughput while also providing 100× increase in energy efficiency over state-of-the-art GPUs [3]." @default.
- W2980456984 created "2019-10-25" @default.
- W2980456984 creator A5014981734 @default.
- W2980456984 creator A5015811754 @default.
- W2980456984 creator A5028455655 @default.
- W2980456984 creator A5042571447 @default.
- W2980456984 creator A5058290381 @default.
- W2980456984 creator A5086723230 @default.
- W2980456984 date "2019-06-01" @default.
- W2980456984 modified "2023-09-23" @default.
- W2980456984 title "Neuro-Inspired Computing: From Resistive Memory to Optics" @default.
- W2980456984 doi "https://doi.org/10.1109/cleoe-eqec.2019.8872657" @default.
- W2980456984 hasPublicationYear "2019" @default.
- W2980456984 type Work @default.
- W2980456984 sameAs 2980456984 @default.
- W2980456984 citedByCount "0" @default.
- W2980456984 crossrefType "proceedings-article" @default.
- W2980456984 hasAuthorship W2980456984A5014981734 @default.
- W2980456984 hasAuthorship W2980456984A5015811754 @default.
- W2980456984 hasAuthorship W2980456984A5028455655 @default.
- W2980456984 hasAuthorship W2980456984A5042571447 @default.
- W2980456984 hasAuthorship W2980456984A5058290381 @default.
- W2980456984 hasAuthorship W2980456984A5086723230 @default.
- W2980456984 hasConcept C111919701 @default.
- W2980456984 hasConcept C118524514 @default.
- W2980456984 hasConcept C123593499 @default.
- W2980456984 hasConcept C149635348 @default.
- W2980456984 hasConcept C154945302 @default.
- W2980456984 hasConcept C157764524 @default.
- W2980456984 hasConcept C164120249 @default.
- W2980456984 hasConcept C173608175 @default.
- W2980456984 hasConcept C194222762 @default.
- W2980456984 hasConcept C23123220 @default.
- W2980456984 hasConcept C2776214188 @default.
- W2980456984 hasConcept C2780513914 @default.
- W2980456984 hasConcept C29984679 @default.
- W2980456984 hasConcept C41008148 @default.
- W2980456984 hasConcept C50644808 @default.
- W2980456984 hasConcept C555944384 @default.
- W2980456984 hasConcept C68339613 @default.
- W2980456984 hasConcept C76155785 @default.
- W2980456984 hasConcept C80469333 @default.
- W2980456984 hasConcept C9390403 @default.
- W2980456984 hasConcept C97854310 @default.
- W2980456984 hasConceptScore W2980456984C111919701 @default.
- W2980456984 hasConceptScore W2980456984C118524514 @default.
- W2980456984 hasConceptScore W2980456984C123593499 @default.
- W2980456984 hasConceptScore W2980456984C149635348 @default.
- W2980456984 hasConceptScore W2980456984C154945302 @default.
- W2980456984 hasConceptScore W2980456984C157764524 @default.
- W2980456984 hasConceptScore W2980456984C164120249 @default.
- W2980456984 hasConceptScore W2980456984C173608175 @default.
- W2980456984 hasConceptScore W2980456984C194222762 @default.
- W2980456984 hasConceptScore W2980456984C23123220 @default.
- W2980456984 hasConceptScore W2980456984C2776214188 @default.
- W2980456984 hasConceptScore W2980456984C2780513914 @default.
- W2980456984 hasConceptScore W2980456984C29984679 @default.
- W2980456984 hasConceptScore W2980456984C41008148 @default.
- W2980456984 hasConceptScore W2980456984C50644808 @default.
- W2980456984 hasConceptScore W2980456984C555944384 @default.
- W2980456984 hasConceptScore W2980456984C68339613 @default.
- W2980456984 hasConceptScore W2980456984C76155785 @default.
- W2980456984 hasConceptScore W2980456984C80469333 @default.
- W2980456984 hasConceptScore W2980456984C9390403 @default.
- W2980456984 hasConceptScore W2980456984C97854310 @default.
- W2980456984 hasLocation W29804569841 @default.
- W2980456984 hasOpenAccess W2980456984 @default.
- W2980456984 hasPrimaryLocation W29804569841 @default.
- W2980456984 hasRelatedWork W1963831041 @default.
- W2980456984 hasRelatedWork W2187752761 @default.
- W2980456984 hasRelatedWork W2233797083 @default.
- W2980456984 hasRelatedWork W2765315405 @default.
- W2980456984 hasRelatedWork W2944959343 @default.
- W2980456984 hasRelatedWork W2956942027 @default.
- W2980456984 hasRelatedWork W2964862330 @default.
- W2980456984 hasRelatedWork W2966825072 @default.
- W2980456984 hasRelatedWork W2971843695 @default.
- W2980456984 hasRelatedWork W2993506981 @default.
- W2980456984 hasRelatedWork W2993912591 @default.
- W2980456984 hasRelatedWork W3000434371 @default.
- W2980456984 hasRelatedWork W3008382534 @default.
- W2980456984 hasRelatedWork W3016292310 @default.
- W2980456984 hasRelatedWork W3030835235 @default.
- W2980456984 hasRelatedWork W3036417437 @default.
- W2980456984 hasRelatedWork W3041406277 @default.
- W2980456984 hasRelatedWork W3118443063 @default.
- W2980456984 hasRelatedWork W3160422373 @default.
- W2980456984 hasRelatedWork W3177180018 @default.
- W2980456984 isParatext "false" @default.
- W2980456984 isRetracted "false" @default.
- W2980456984 magId "2980456984" @default.
- W2980456984 workType "article" @default.