Matches in SemOpenAlex for { <https://semopenalex.org/work/W1972092419> ?p ?o ?g. }
- W1972092419 endingPage "1942" @default.
- W1972092419 startingPage "1917" @default.
- W1972092419 abstract "A recurrent network is proposed with the ability to bind image features into a unified surface representation within a single layer and without capacity limitations or border effects. A group of cells belonging to the same object or surface is labeled with the same activity amplitude, while cells in different groups are kept segregated due to lateral inhibition. Labeling is achieved by activity spreading through local excitatory connections. In order to prevent uncontrolled spreading, a separate network computes the intensity difference between neighboring locations and signals the presence of the surface boundary, which constrains local excitation. The quality of surface representation is not compromised due to the self-excitation. The model is also applied on gray-level images. In order to remove small, noisy regions, a feedforward network is proposed that computes the size of surfaces. Size estimation is based on the difference of dendritic inhibition in lateral excitatory and inhibitory pathways, which allows the network to selectively integrate signals only from cells with the same activity amplitude. When the output of the size estimation network is combined with the recurrent network, good segmentation results are obtained. Both networks are based on biophysically realistic mechanisms such as dendritic inhibition and multiplicative integration among different dendritic branches." @default.
- W1972092419 created "2016-06-24" @default.
- W1972092419 creator A5007059241 @default.
- W1972092419 date "2004-09-01" @default.
- W1972092419 modified "2023-10-16" @default.
- W1972092419 title "Recurrent Network with Large Representational Capacity" @default.
- W1972092419 cites W1491997873 @default.
- W1972092419 cites W1543794893 @default.
- W1972092419 cites W1594682360 @default.
- W1972092419 cites W1964382381 @default.
- W1972092419 cites W1979637432 @default.
- W1972092419 cites W1984533126 @default.
- W1972092419 cites W1985472329 @default.
- W1972092419 cites W1988760030 @default.
- W1972092419 cites W1996773027 @default.
- W1972092419 cites W2016189779 @default.
- W1972092419 cites W2024390075 @default.
- W1972092419 cites W2028680553 @default.
- W1972092419 cites W2030397019 @default.
- W1972092419 cites W2035051040 @default.
- W1972092419 cites W2038146945 @default.
- W1972092419 cites W2042076735 @default.
- W1972092419 cites W2044641672 @default.
- W1972092419 cites W2047929095 @default.
- W1972092419 cites W2053410789 @default.
- W1972092419 cites W2054802006 @default.
- W1972092419 cites W2056908494 @default.
- W1972092419 cites W2064852296 @default.
- W1972092419 cites W2066877541 @default.
- W1972092419 cites W2078835982 @default.
- W1972092419 cites W2091354315 @default.
- W1972092419 cites W2093353037 @default.
- W1972092419 cites W2097567488 @default.
- W1972092419 cites W2101933716 @default.
- W1972092419 cites W2105096388 @default.
- W1972092419 cites W2106180805 @default.
- W1972092419 cites W2109887449 @default.
- W1972092419 cites W2112332687 @default.
- W1972092419 cites W2113291211 @default.
- W1972092419 cites W2114587936 @default.
- W1972092419 cites W2114588745 @default.
- W1972092419 cites W2120907531 @default.
- W1972092419 cites W2120910962 @default.
- W1972092419 cites W2124971912 @default.
- W1972092419 cites W2125988384 @default.
- W1972092419 cites W2130260587 @default.
- W1972092419 cites W2131470433 @default.
- W1972092419 cites W2138558323 @default.
- W1972092419 cites W2139780773 @default.
- W1972092419 cites W2140448023 @default.
- W1972092419 cites W2142361063 @default.
- W1972092419 cites W2143961210 @default.
- W1972092419 cites W2144764737 @default.
- W1972092419 cites W2145211411 @default.
- W1972092419 cites W2150052800 @default.
- W1972092419 cites W2155941614 @default.
- W1972092419 cites W2156963988 @default.
- W1972092419 cites W2159353177 @default.
- W1972092419 cites W2160038311 @default.
- W1972092419 cites W2162002414 @default.
- W1972092419 cites W2164649534 @default.
- W1972092419 cites W2165427779 @default.
- W1972092419 cites W2166198088 @default.
- W1972092419 cites W2166431160 @default.
- W1972092419 cites W2169710839 @default.
- W1972092419 cites W2171793409 @default.
- W1972092419 cites W4213285154 @default.
- W1972092419 cites W4234969819 @default.
- W1972092419 cites W4237582627 @default.
- W1972092419 cites W4251439160 @default.
- W1972092419 doi "https://doi.org/10.1162/0899766041336422" @default.
- W1972092419 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/15265328" @default.
- W1972092419 hasPublicationYear "2004" @default.
- W1972092419 type Work @default.
- W1972092419 sameAs 1972092419 @default.
- W1972092419 citedByCount "7" @default.
- W1972092419 countsByYear W19720924192018 @default.
- W1972092419 countsByYear W19720924192022 @default.
- W1972092419 crossrefType "journal-article" @default.
- W1972092419 hasAuthorship W1972092419A5007059241 @default.
- W1972092419 hasConcept C104122410 @default.
- W1972092419 hasConcept C112592302 @default.
- W1972092419 hasConcept C11413529 @default.
- W1972092419 hasConcept C120665830 @default.
- W1972092419 hasConcept C121332964 @default.
- W1972092419 hasConcept C127413603 @default.
- W1972092419 hasConcept C133731056 @default.
- W1972092419 hasConcept C134306372 @default.
- W1972092419 hasConcept C153180895 @default.
- W1972092419 hasConcept C154945302 @default.
- W1972092419 hasConcept C169760540 @default.
- W1972092419 hasConcept C17077164 @default.
- W1972092419 hasConcept C17744445 @default.
- W1972092419 hasConcept C180205008 @default.
- W1972092419 hasConcept C186060115 @default.
- W1972092419 hasConcept C199539241 @default.
- W1972092419 hasConcept C2776359362 @default.
- W1972092419 hasConcept C33923547 @default.