Matches in SemOpenAlex for { <https://semopenalex.org/work/W1825672851> ?p ?o ?g. }
- W1825672851 abstract "Multipliers are the most space and power-hungry arithmetic operators of the digital implementation of deep neural networks. We train a set of state-of-the-art neural networks (Maxout networks) on three benchmark datasets: MNIST, CIFAR-10 and SVHN. They are trained with three distinct formats: floating point, fixed point and dynamic fixed point. For each of those datasets and for each of those formats, we assess the impact of the precision of the multiplications on the final error after training. We find that very low precision is sufficient not just for running trained networks but also for training them. For example, it is possible to train Maxout networks with 10 bits multiplications." @default.
- W1825672851 created "2016-06-24" @default.
- W1825672851 creator A5039449234 @default.
- W1825672851 creator A5067086966 @default.
- W1825672851 creator A5086198262 @default.
- W1825672851 date "2014-12-22" @default.
- W1825672851 modified "2023-10-01" @default.
- W1825672851 title "Training deep neural networks with low precision multiplications" @default.
- W1825672851 cites W1492459858 @default.
- W1825672851 cites W1720204209 @default.
- W1825672851 cites W1904365287 @default.
- W1825672851 cites W1907282891 @default.
- W1825672851 cites W2048266589 @default.
- W1825672851 cites W2074488431 @default.
- W1825672851 cites W2112796928 @default.
- W1825672851 cites W2122221396 @default.
- W1825672851 cites W2149428536 @default.
- W1825672851 cites W2153412052 @default.
- W1825672851 cites W2153846939 @default.
- W1825672851 cites W2168231600 @default.
- W1825672851 cites W2168839239 @default.
- W1825672851 cites W2335728318 @default.
- W1825672851 cites W2546302380 @default.
- W1825672851 cites W2963374099 @default.
- W1825672851 cites W3118608800 @default.
- W1825672851 cites W587794757 @default.
- W1825672851 hasPublicationYear "2014" @default.
- W1825672851 type Work @default.
- W1825672851 sameAs 1825672851 @default.
- W1825672851 citedByCount "139" @default.
- W1825672851 countsByYear W18256728512015 @default.
- W1825672851 countsByYear W18256728512016 @default.
- W1825672851 countsByYear W18256728512017 @default.
- W1825672851 countsByYear W18256728512018 @default.
- W1825672851 countsByYear W18256728512019 @default.
- W1825672851 countsByYear W18256728512020 @default.
- W1825672851 countsByYear W18256728512021 @default.
- W1825672851 countsByYear W18256728512022 @default.
- W1825672851 crossrefType "posted-content" @default.
- W1825672851 hasAuthorship W1825672851A5039449234 @default.
- W1825672851 hasAuthorship W1825672851A5067086966 @default.
- W1825672851 hasAuthorship W1825672851A5086198262 @default.
- W1825672851 hasConcept C108583219 @default.
- W1825672851 hasConcept C11413529 @default.
- W1825672851 hasConcept C119857082 @default.
- W1825672851 hasConcept C13280743 @default.
- W1825672851 hasConcept C154945302 @default.
- W1825672851 hasConcept C177264268 @default.
- W1825672851 hasConcept C185798385 @default.
- W1825672851 hasConcept C190502265 @default.
- W1825672851 hasConcept C199360897 @default.
- W1825672851 hasConcept C205649164 @default.
- W1825672851 hasConcept C2524010 @default.
- W1825672851 hasConcept C28719098 @default.
- W1825672851 hasConcept C2984842247 @default.
- W1825672851 hasConcept C33923547 @default.
- W1825672851 hasConcept C41008148 @default.
- W1825672851 hasConcept C50644808 @default.
- W1825672851 hasConcept C51632099 @default.
- W1825672851 hasConcept C84211073 @default.
- W1825672851 hasConceptScore W1825672851C108583219 @default.
- W1825672851 hasConceptScore W1825672851C11413529 @default.
- W1825672851 hasConceptScore W1825672851C119857082 @default.
- W1825672851 hasConceptScore W1825672851C13280743 @default.
- W1825672851 hasConceptScore W1825672851C154945302 @default.
- W1825672851 hasConceptScore W1825672851C177264268 @default.
- W1825672851 hasConceptScore W1825672851C185798385 @default.
- W1825672851 hasConceptScore W1825672851C190502265 @default.
- W1825672851 hasConceptScore W1825672851C199360897 @default.
- W1825672851 hasConceptScore W1825672851C205649164 @default.
- W1825672851 hasConceptScore W1825672851C2524010 @default.
- W1825672851 hasConceptScore W1825672851C28719098 @default.
- W1825672851 hasConceptScore W1825672851C2984842247 @default.
- W1825672851 hasConceptScore W1825672851C33923547 @default.
- W1825672851 hasConceptScore W1825672851C41008148 @default.
- W1825672851 hasConceptScore W1825672851C50644808 @default.
- W1825672851 hasConceptScore W1825672851C51632099 @default.
- W1825672851 hasConceptScore W1825672851C84211073 @default.
- W1825672851 hasLocation W18256728511 @default.
- W1825672851 hasOpenAccess W1825672851 @default.
- W1825672851 hasPrimaryLocation W18256728511 @default.
- W1825672851 hasRelatedWork W1594170634 @default.
- W1825672851 hasRelatedWork W1686810756 @default.
- W1825672851 hasRelatedWork W1724438581 @default.
- W1825672851 hasRelatedWork W2097117768 @default.
- W1825672851 hasRelatedWork W2108598243 @default.
- W1825672851 hasRelatedWork W2112796928 @default.
- W1825672851 hasRelatedWork W2117539524 @default.
- W1825672851 hasRelatedWork W2163605009 @default.
- W1825672851 hasRelatedWork W2194775991 @default.
- W1825672851 hasRelatedWork W2279098554 @default.
- W1825672851 hasRelatedWork W2286365479 @default.
- W1825672851 hasRelatedWork W2300242332 @default.
- W1825672851 hasRelatedWork W2319920447 @default.
- W1825672851 hasRelatedWork W2469490737 @default.
- W1825672851 hasRelatedWork W2612445135 @default.
- W1825672851 hasRelatedWork W2963114950 @default.
- W1825672851 hasRelatedWork W2963374099 @default.
- W1825672851 hasRelatedWork W2963674932 @default.
- W1825672851 hasRelatedWork W2964299589 @default.