Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951472764> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2951472764 abstract "We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and very few tunable parameters, the method has strong potential for applications requiring frequent retraining or online training. The approach is characterized by (a) convolutional filters based on biologically inspired visual processing filters, (b) randomly-valued classifier-stage input weights, (c) use of least squares regression to train the classifier output weights in a single batch, and (d) linear classifier-stage output units. We demonstrate the efficacy of the method by applying it to image classification. Our results match existing state-of-the-art results on the MNIST (0.37% error) and NORB-small (2.2% error) image classification databases, but with very fast training times compared to standard deep network approaches. The network's performance on the Google Street View House Number (SVHN) (4% error) database is also competitive with state-of-the art methods." @default.
- W2951472764 created "2019-06-27" @default.
- W2951472764 creator A5000677611 @default.
- W2951472764 creator A5022699451 @default.
- W2951472764 date "2015-03-16" @default.
- W2951472764 modified "2023-09-27" @default.
- W2951472764 title "Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network" @default.
- W2951472764 cites W1505186732 @default.
- W2951472764 cites W1625160166 @default.
- W2951472764 cites W1737787488 @default.
- W2951472764 cites W1809320442 @default.
- W2951472764 cites W2016708835 @default.
- W2951472764 cites W2072057046 @default.
- W2951472764 cites W2076063813 @default.
- W2951472764 cites W2101158159 @default.
- W2951472764 cites W2101674911 @default.
- W2951472764 cites W2104242071 @default.
- W2951472764 cites W2112796928 @default.
- W2951472764 cites W2118858186 @default.
- W2951472764 cites W2132424367 @default.
- W2951472764 cites W2134557905 @default.
- W2951472764 cites W2134603844 @default.
- W2951472764 cites W2147860648 @default.
- W2951472764 cites W2153232138 @default.
- W2951472764 cites W2155910151 @default.
- W2951472764 cites W2156163116 @default.
- W2951472764 cites W2184852195 @default.
- W2951472764 cites W2949578333 @default.
- W2951472764 cites W2963542991 @default.
- W2951472764 cites W45732403 @default.
- W2951472764 cites W639309485 @default.
- W2951472764 hasPublicationYear "2015" @default.
- W2951472764 type Work @default.
- W2951472764 sameAs 2951472764 @default.
- W2951472764 citedByCount "2" @default.
- W2951472764 countsByYear W29514727642015 @default.
- W2951472764 countsByYear W29514727642016 @default.
- W2951472764 crossrefType "posted-content" @default.
- W2951472764 hasAuthorship W2951472764A5000677611 @default.
- W2951472764 hasAuthorship W2951472764A5022699451 @default.
- W2951472764 hasConcept C108583219 @default.
- W2951472764 hasConcept C115961682 @default.
- W2951472764 hasConcept C119857082 @default.
- W2951472764 hasConcept C144133560 @default.
- W2951472764 hasConcept C153180895 @default.
- W2951472764 hasConcept C154945302 @default.
- W2951472764 hasConcept C155202549 @default.
- W2951472764 hasConcept C190502265 @default.
- W2951472764 hasConcept C2778712577 @default.
- W2951472764 hasConcept C41008148 @default.
- W2951472764 hasConcept C50644808 @default.
- W2951472764 hasConcept C75294576 @default.
- W2951472764 hasConcept C81363708 @default.
- W2951472764 hasConcept C95623464 @default.
- W2951472764 hasConceptScore W2951472764C108583219 @default.
- W2951472764 hasConceptScore W2951472764C115961682 @default.
- W2951472764 hasConceptScore W2951472764C119857082 @default.
- W2951472764 hasConceptScore W2951472764C144133560 @default.
- W2951472764 hasConceptScore W2951472764C153180895 @default.
- W2951472764 hasConceptScore W2951472764C154945302 @default.
- W2951472764 hasConceptScore W2951472764C155202549 @default.
- W2951472764 hasConceptScore W2951472764C190502265 @default.
- W2951472764 hasConceptScore W2951472764C2778712577 @default.
- W2951472764 hasConceptScore W2951472764C41008148 @default.
- W2951472764 hasConceptScore W2951472764C50644808 @default.
- W2951472764 hasConceptScore W2951472764C75294576 @default.
- W2951472764 hasConceptScore W2951472764C81363708 @default.
- W2951472764 hasConceptScore W2951472764C95623464 @default.
- W2951472764 hasLocation W29514727641 @default.
- W2951472764 hasOpenAccess W2951472764 @default.
- W2951472764 hasPrimaryLocation W29514727641 @default.
- W2951472764 hasRelatedWork W1737787488 @default.
- W2951472764 hasRelatedWork W2112796928 @default.
- W2951472764 hasRelatedWork W2145065314 @default.
- W2951472764 hasRelatedWork W2267038056 @default.
- W2951472764 hasRelatedWork W2267244539 @default.
- W2951472764 hasRelatedWork W2617903083 @default.
- W2951472764 hasRelatedWork W2748415341 @default.
- W2951472764 hasRelatedWork W2763600295 @default.
- W2951472764 hasRelatedWork W2769937543 @default.
- W2951472764 hasRelatedWork W2889631368 @default.
- W2951472764 hasRelatedWork W2891912008 @default.
- W2951472764 hasRelatedWork W2900242584 @default.
- W2951472764 hasRelatedWork W2913263636 @default.
- W2951472764 hasRelatedWork W2963331432 @default.
- W2951472764 hasRelatedWork W3013555638 @default.
- W2951472764 hasRelatedWork W3016258355 @default.
- W2951472764 hasRelatedWork W3019513356 @default.
- W2951472764 hasRelatedWork W3090563815 @default.
- W2951472764 hasRelatedWork W3091400040 @default.
- W2951472764 hasRelatedWork W3120923100 @default.
- W2951472764 isParatext "false" @default.
- W2951472764 isRetracted "false" @default.
- W2951472764 magId "2951472764" @default.
- W2951472764 workType "article" @default.