Matches in SemOpenAlex for { <https://semopenalex.org/work/W2087514981> ?p ?o ?g. }
- W2087514981 endingPage "e81813" @default.
- W2087514981 startingPage "e81813" @default.
- W2087514981 abstract "About ten years ago, HMAX was proposed as a simple and biologically feasible model for object recognition, based on how the visual cortex processes information. However, the model does not encompass sparse firing, which is a hallmark of neurons at all stages of the visual pathway. The current paper presents an improved model, called sparse HMAX, which integrates sparse firing. This model is able to learn higher-level features of objects on unlabeled training images. Unlike most other deep learning models that explicitly address global structure of images in every layer, sparse HMAX addresses local to global structure gradually along the hierarchy by applying patch-based learning to the output of the previous layer. As a consequence, the learning method can be standard sparse coding (SSC) or independent component analysis (ICA), two techniques deeply rooted in neuroscience. What makes SSC and ICA applicable at higher levels is the introduction of linear higher-order statistical regularities by max pooling. After training, high-level units display sparse, invariant selectivity for particular individuals or for image categories like those observed in human inferior temporal cortex (ITC) and medial temporal lobe (MTL). Finally, on an image classification benchmark, sparse HMAX outperforms the original HMAX by a large margin, suggesting its great potential for computer vision." @default.
- W2087514981 created "2016-06-24" @default.
- W2087514981 creator A5004579631 @default.
- W2087514981 creator A5006247366 @default.
- W2087514981 creator A5011877804 @default.
- W2087514981 creator A5034054749 @default.
- W2087514981 date "2014-01-02" @default.
- W2087514981 modified "2023-10-18" @default.
- W2087514981 title "Sparsity-Regularized HMAX for Visual Recognition" @default.
- W2087514981 cites W104847522 @default.
- W2087514981 cites W109907426 @default.
- W2087514981 cites W1526492552 @default.
- W2087514981 cites W1624854622 @default.
- W2087514981 cites W1972660505 @default.
- W2087514981 cites W2005876975 @default.
- W2087514981 cites W2014930414 @default.
- W2087514981 cites W2020719522 @default.
- W2087514981 cites W2022930567 @default.
- W2087514981 cites W2056167764 @default.
- W2087514981 cites W2072016696 @default.
- W2087514981 cites W2086664483 @default.
- W2087514981 cites W2097620723 @default.
- W2087514981 cites W2101295242 @default.
- W2087514981 cites W2101926813 @default.
- W2087514981 cites W2105464770 @default.
- W2087514981 cites W2105464873 @default.
- W2087514981 cites W2108138754 @default.
- W2087514981 cites W2112575974 @default.
- W2087514981 cites W2116064496 @default.
- W2087514981 cites W2117731089 @default.
- W2087514981 cites W2121975859 @default.
- W2087514981 cites W2123649031 @default.
- W2087514981 cites W2124486835 @default.
- W2087514981 cites W2130325614 @default.
- W2087514981 cites W2132172482 @default.
- W2087514981 cites W2141200610 @default.
- W2087514981 cites W2144982973 @default.
- W2087514981 cites W2145889472 @default.
- W2087514981 cites W2148165961 @default.
- W2087514981 cites W2149194912 @default.
- W2087514981 cites W2151103935 @default.
- W2087514981 cites W2152172623 @default.
- W2087514981 cites W2293078015 @default.
- W2087514981 cites W4248877029 @default.
- W2087514981 cites W4256041663 @default.
- W2087514981 doi "https://doi.org/10.1371/journal.pone.0081813" @default.
- W2087514981 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/3879257" @default.
- W2087514981 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/24392078" @default.
- W2087514981 hasPublicationYear "2014" @default.
- W2087514981 type Work @default.
- W2087514981 sameAs 2087514981 @default.
- W2087514981 citedByCount "56" @default.
- W2087514981 countsByYear W20875149812014 @default.
- W2087514981 countsByYear W20875149812015 @default.
- W2087514981 countsByYear W20875149812016 @default.
- W2087514981 countsByYear W20875149812017 @default.
- W2087514981 countsByYear W20875149812018 @default.
- W2087514981 countsByYear W20875149812019 @default.
- W2087514981 countsByYear W20875149812020 @default.
- W2087514981 countsByYear W20875149812021 @default.
- W2087514981 countsByYear W20875149812022 @default.
- W2087514981 countsByYear W20875149812023 @default.
- W2087514981 crossrefType "journal-article" @default.
- W2087514981 hasAuthorship W2087514981A5004579631 @default.
- W2087514981 hasAuthorship W2087514981A5006247366 @default.
- W2087514981 hasAuthorship W2087514981A5011877804 @default.
- W2087514981 hasAuthorship W2087514981A5034054749 @default.
- W2087514981 hasBestOaLocation W20875149811 @default.
- W2087514981 hasConcept C108583219 @default.
- W2087514981 hasConcept C119857082 @default.
- W2087514981 hasConcept C124066611 @default.
- W2087514981 hasConcept C153180895 @default.
- W2087514981 hasConcept C154945302 @default.
- W2087514981 hasConcept C15744967 @default.
- W2087514981 hasConcept C169760540 @default.
- W2087514981 hasConcept C2779345533 @default.
- W2087514981 hasConcept C2993858690 @default.
- W2087514981 hasConcept C41008148 @default.
- W2087514981 hasConcept C52622490 @default.
- W2087514981 hasConcept C64876066 @default.
- W2087514981 hasConcept C70437156 @default.
- W2087514981 hasConcept C77637269 @default.
- W2087514981 hasConceptScore W2087514981C108583219 @default.
- W2087514981 hasConceptScore W2087514981C119857082 @default.
- W2087514981 hasConceptScore W2087514981C124066611 @default.
- W2087514981 hasConceptScore W2087514981C153180895 @default.
- W2087514981 hasConceptScore W2087514981C154945302 @default.
- W2087514981 hasConceptScore W2087514981C15744967 @default.
- W2087514981 hasConceptScore W2087514981C169760540 @default.
- W2087514981 hasConceptScore W2087514981C2779345533 @default.
- W2087514981 hasConceptScore W2087514981C2993858690 @default.
- W2087514981 hasConceptScore W2087514981C41008148 @default.
- W2087514981 hasConceptScore W2087514981C52622490 @default.
- W2087514981 hasConceptScore W2087514981C64876066 @default.
- W2087514981 hasConceptScore W2087514981C70437156 @default.
- W2087514981 hasConceptScore W2087514981C77637269 @default.
- W2087514981 hasIssue "1" @default.
- W2087514981 hasLocation W20875149811 @default.