FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891938284> ?p ?o ?g. }

• W2891938284 abstract "Abstract Deep artificial neural networks with spatially repeated processing (a.k.a., deep convolutional ANNs) have been established as the best class of candidate models of visual processing in primate ventral visual processing stream. Over the past five years, these ANNs have evolved from a simple feedforward eight-layer architecture in AlexNet to extremely deep and branching NAS-Net architectures, demonstrating increasingly better object categorization performance and increasingly better explanatory power of both neural and behavioral responses. However, from the neuroscientist’s point of view, the relationship between such very deep architectures and the ventral visual pathway is incomplete in at least two ways. On the one hand, current state-of-the-art ANNs appear to be too complex (e.g., now over 100 levels) compared with the relatively shallow cortical hierarchy (4-8 levels), which makes it difficult to map their elements to those in the ventral visual stream and to understand what they are doing. On the other hand, current state-of-the-art ANNs appear to be not complex enough in that they lack recurrent connections and the resulting neural response dynamics that are commonplace in the ventral visual stream. Here we describe our ongoing efforts to resolve both of these issues by developing a “CORnet” family of deep neural network architectures. Rather than just seeking high object recognition performance (as the state-of-the-art ANNs above), we instead try to reduce the model family to its most important elements and then gradually build new ANNs with recurrent and skip connections while monitoring both performance and the match between each new CORnet model and a large body of primate brain and behavioral data. We report here that our current best ANN model derived from this approach (CORnet-S) is among the top models on Brain-Score, a composite benchmark for comparing models to the brain, but is simpler than other deep ANNs in terms of the number of convolutions performed along the longest path of information processing in the model. All CORnet models are available at github.com/dicarlolab/CORnet, and we plan to up-date this manuscript and the available models in this family as they are produced." @default.
• W2891938284 created "2018-09-27" @default.
• W2891938284 creator A5000014892 @default.
• W2891938284 creator A5018121577 @default.
• W2891938284 creator A5025347577 @default.
• W2891938284 creator A5030840440 @default.
• W2891938284 creator A5034283312 @default.
• W2891938284 creator A5058188874 @default.
• W2891938284 date "2018-09-04" @default.
• W2891938284 modified "2023-10-17" @default.
• W2891938284 title "CORnet: Modeling the Neural Mechanisms of Core Object Recognition" @default.
• W2891938284 cites W1715013381 @default.
• W2891938284 cites W1803469231 @default.
• W2891938284 cites W1925018227 @default.
• W2891938284 cites W2030622216 @default.
• W2891938284 cites W2040036684 @default.
• W2891938284 cites W2058616551 @default.
• W2891938284 cites W2101926813 @default.
• W2891938284 cites W2102022426 @default.
• W2891938284 cites W2104698815 @default.
• W2891938284 cites W2113466552 @default.
• W2891938284 cites W2116360511 @default.
• W2891938284 cites W2117539524 @default.
• W2891938284 cites W2120907531 @default.
• W2891938284 cites W2121008432 @default.
• W2891938284 cites W2132172482 @default.
• W2891938284 cites W2145889472 @default.
• W2891938284 cites W2149194912 @default.
• W2891938284 cites W2151823074 @default.
• W2891938284 cites W2162950292 @default.
• W2891938284 cites W2166206801 @default.
• W2891938284 cites W2169134378 @default.
• W2891938284 cites W2274405424 @default.
• W2891938284 cites W2343204383 @default.
• W2891938284 cites W2597327304 @default.
• W2891938284 cites W2623160143 @default.
• W2891938284 cites W2760951817 @default.
• W2891938284 cites W2773697142 @default.
• W2891938284 cites W2787827409 @default.
• W2891938284 cites W2798245336 @default.
• W2891938284 cites W2810416197 @default.
• W2891938284 cites W2883033711 @default.
• W2891938284 cites W2887228117 @default.
• W2891938284 cites W2892147425 @default.
• W2891938284 doi "https://doi.org/10.1101/408385" @default.
• W2891938284 hasPublicationYear "2018" @default.
• W2891938284 type Work @default.
• W2891938284 sameAs 2891938284 @default.
• W2891938284 citedByCount "95" @default.
• W2891938284 countsByYear W28919382842019 @default.
• W2891938284 countsByYear W28919382842020 @default.
• W2891938284 countsByYear W28919382842021 @default.
• W2891938284 countsByYear W28919382842022 @default.
• W2891938284 countsByYear W28919382842023 @default.
• W2891938284 crossrefType "posted-content" @default.
• W2891938284 hasAuthorship W2891938284A5000014892 @default.
• W2891938284 hasAuthorship W2891938284A5018121577 @default.
• W2891938284 hasAuthorship W2891938284A5025347577 @default.
• W2891938284 hasAuthorship W2891938284A5030840440 @default.
• W2891938284 hasAuthorship W2891938284A5034283312 @default.
• W2891938284 hasAuthorship W2891938284A5058188874 @default.
• W2891938284 hasBestOaLocation W28919382841 @default.
• W2891938284 hasConcept C108583219 @default.
• W2891938284 hasConcept C153180895 @default.
• W2891938284 hasConcept C154945302 @default.
• W2891938284 hasConcept C15744967 @default.
• W2891938284 hasConcept C162324750 @default.
• W2891938284 hasConcept C169760540 @default.
• W2891938284 hasConcept C26760741 @default.
• W2891938284 hasConcept C2778251979 @default.
• W2891938284 hasConcept C2781238097 @default.
• W2891938284 hasConcept C2984842247 @default.
• W2891938284 hasConcept C31170391 @default.
• W2891938284 hasConcept C34447519 @default.
• W2891938284 hasConcept C41008148 @default.
• W2891938284 hasConcept C50644808 @default.
• W2891938284 hasConcept C64876066 @default.
• W2891938284 hasConcept C81363708 @default.
• W2891938284 hasConcept C94124525 @default.
• W2891938284 hasConceptScore W2891938284C108583219 @default.
• W2891938284 hasConceptScore W2891938284C153180895 @default.
• W2891938284 hasConceptScore W2891938284C154945302 @default.
• W2891938284 hasConceptScore W2891938284C15744967 @default.
• W2891938284 hasConceptScore W2891938284C162324750 @default.
• W2891938284 hasConceptScore W2891938284C169760540 @default.
• W2891938284 hasConceptScore W2891938284C26760741 @default.
• W2891938284 hasConceptScore W2891938284C2778251979 @default.
• W2891938284 hasConceptScore W2891938284C2781238097 @default.
• W2891938284 hasConceptScore W2891938284C2984842247 @default.
• W2891938284 hasConceptScore W2891938284C31170391 @default.
• W2891938284 hasConceptScore W2891938284C34447519 @default.
• W2891938284 hasConceptScore W2891938284C41008148 @default.
• W2891938284 hasConceptScore W2891938284C50644808 @default.
• W2891938284 hasConceptScore W2891938284C64876066 @default.
• W2891938284 hasConceptScore W2891938284C81363708 @default.
• W2891938284 hasConceptScore W2891938284C94124525 @default.
• W2891938284 hasLocation W28919382841 @default.
• W2891938284 hasLocation W28919382842 @default.
• W2891938284 hasOpenAccess W2891938284 @default.
• W2891938284 hasPrimaryLocation W28919382841 @default.

• next