Matches in SemOpenAlex for { <https://semopenalex.org/work/W2108806771> ?p ?o ?g. }
- W2108806771 endingPage "1394" @default.
- W2108806771 startingPage "1387" @default.
- W2108806771 abstract "We consider the problem of object recognition with a large number of classes. In order to overcome the low amount of labeled examples available in this setting, we introduce a new feature learning and extraction procedure based on a factor model we call spike-and-slab sparse coding (S3C). Prior work on S3C has not prioritized the ability to exploit parallel architectures and scale S3C to the enormous problem sizes needed for object recognition. We present a novel inference procedure for appropriate for use with GPUs which allows us to dramatically increase both the training set size and the amount of latent factors that S3C may be trained with. We demonstrate that this approach improves upon the supervised learning capabilities of both sparse coding and the spike-and-slab Restricted Boltzmann Machine (ssRBM) on the CIFAR-10 dataset. We use the CIFAR-100 dataset to demonstrate that our method scales to large numbers of classes better than previous methods. Finally, we use our method to win the NIPS 2011 Workshop on Challenges In Learning Hierarchical Models' Transfer Learning Challenge." @default.
- W2108806771 created "2016-06-24" @default.
- W2108806771 creator A5004271128 @default.
- W2108806771 creator A5031185465 @default.
- W2108806771 creator A5086198262 @default.
- W2108806771 date "2012-06-26" @default.
- W2108806771 modified "2023-10-03" @default.
- W2108806771 title "Large-Scale Feature Learning With Spike-and-Slab Sparse Coding" @default.
- W2108806771 cites W1511986666 @default.
- W2108806771 cites W1813659000 @default.
- W2108806771 cites W189596042 @default.
- W2108806771 cites W1999974018 @default.
- W2108806771 cites W2020719522 @default.
- W2108806771 cites W2036054070 @default.
- W2108806771 cites W2072128103 @default.
- W2108806771 cites W2104163628 @default.
- W2108806771 cites W2105464873 @default.
- W2108806771 cites W2110798204 @default.
- W2108806771 cites W2122922389 @default.
- W2108806771 cites W2130984546 @default.
- W2108806771 cites W2136922672 @default.
- W2108806771 cites W2138311613 @default.
- W2108806771 cites W2140433132 @default.
- W2108806771 cites W2141200610 @default.
- W2108806771 cites W2155676512 @default.
- W2108806771 cites W2160142299 @default.
- W2108806771 cites W2169488311 @default.
- W2108806771 cites W2172172255 @default.
- W2108806771 cites W2184852195 @default.
- W2108806771 cites W2289330286 @default.
- W2108806771 cites W2530114498 @default.
- W2108806771 cites W2567948266 @default.
- W2108806771 cites W3118608800 @default.
- W2108806771 hasPublicationYear "2012" @default.
- W2108806771 type Work @default.
- W2108806771 sameAs 2108806771 @default.
- W2108806771 citedByCount "19" @default.
- W2108806771 countsByYear W21088067712012 @default.
- W2108806771 countsByYear W21088067712013 @default.
- W2108806771 countsByYear W21088067712014 @default.
- W2108806771 countsByYear W21088067712015 @default.
- W2108806771 countsByYear W21088067712016 @default.
- W2108806771 countsByYear W21088067712021 @default.
- W2108806771 crossrefType "proceedings-article" @default.
- W2108806771 hasAuthorship W2108806771A5004271128 @default.
- W2108806771 hasAuthorship W2108806771A5031185465 @default.
- W2108806771 hasAuthorship W2108806771A5086198262 @default.
- W2108806771 hasConcept C105795698 @default.
- W2108806771 hasConcept C115903868 @default.
- W2108806771 hasConcept C119857082 @default.
- W2108806771 hasConcept C153180895 @default.
- W2108806771 hasConcept C154945302 @default.
- W2108806771 hasConcept C165696696 @default.
- W2108806771 hasConcept C179518139 @default.
- W2108806771 hasConcept C2776214188 @default.
- W2108806771 hasConcept C2781390188 @default.
- W2108806771 hasConcept C33923547 @default.
- W2108806771 hasConcept C38652104 @default.
- W2108806771 hasConcept C41008148 @default.
- W2108806771 hasConcept C52622490 @default.
- W2108806771 hasConcept C59404180 @default.
- W2108806771 hasConcept C64876066 @default.
- W2108806771 hasConcept C77637269 @default.
- W2108806771 hasConceptScore W2108806771C105795698 @default.
- W2108806771 hasConceptScore W2108806771C115903868 @default.
- W2108806771 hasConceptScore W2108806771C119857082 @default.
- W2108806771 hasConceptScore W2108806771C153180895 @default.
- W2108806771 hasConceptScore W2108806771C154945302 @default.
- W2108806771 hasConceptScore W2108806771C165696696 @default.
- W2108806771 hasConceptScore W2108806771C179518139 @default.
- W2108806771 hasConceptScore W2108806771C2776214188 @default.
- W2108806771 hasConceptScore W2108806771C2781390188 @default.
- W2108806771 hasConceptScore W2108806771C33923547 @default.
- W2108806771 hasConceptScore W2108806771C38652104 @default.
- W2108806771 hasConceptScore W2108806771C41008148 @default.
- W2108806771 hasConceptScore W2108806771C52622490 @default.
- W2108806771 hasConceptScore W2108806771C59404180 @default.
- W2108806771 hasConceptScore W2108806771C64876066 @default.
- W2108806771 hasConceptScore W2108806771C77637269 @default.
- W2108806771 hasLocation W21088067711 @default.
- W2108806771 hasOpenAccess W2108806771 @default.
- W2108806771 hasPrimaryLocation W21088067711 @default.
- W2108806771 hasRelatedWork W1567512734 @default.
- W2108806771 hasRelatedWork W1761606332 @default.
- W2108806771 hasRelatedWork W189596042 @default.
- W2108806771 hasRelatedWork W2025768430 @default.
- W2108806771 hasRelatedWork W2095705004 @default.
- W2108806771 hasRelatedWork W2100495367 @default.
- W2108806771 hasRelatedWork W2101926813 @default.
- W2108806771 hasRelatedWork W2110798204 @default.
- W2108806771 hasRelatedWork W2113606819 @default.
- W2108806771 hasRelatedWork W2122922389 @default.
- W2108806771 hasRelatedWork W2135046866 @default.
- W2108806771 hasRelatedWork W2136922672 @default.
- W2108806771 hasRelatedWork W2145094598 @default.
- W2108806771 hasRelatedWork W2145889472 @default.
- W2108806771 hasRelatedWork W2155676512 @default.
- W2108806771 hasRelatedWork W2163605009 @default.