FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1625958017> ?p ?o ?g. }

• W1625958017 endingPage "3457" @default.
• W1625958017 startingPage "3444" @default.
• W1625958017 abstract "Three important properties of a classification machinery are: (i) the system preserves the core information of the input data; (ii) the training examples convey information about unseen data; and (iii) the system is able to treat differently points from different classes. In this work we show that these fundamental properties are satisfied by the architecture of deep neural networks. We formally prove that these networks with random Gaussian weights perform a distance-preserving embedding of the data, with a special treatment for in-class and out-of-class data. Similar points at the input of the network are likely to have a similar output. The theoretical analysis of deep networks here presented exploits tools used in the compressed sensing and dictionary learning literature, thereby making a formal connection between these important topics. The derived results allow drawing conclusions on the metric learning properties of the network and their relation to its structure, as well as providing bounds on the required size of the training set such that the training examples would represent faithfully the unseen data. The results are validated with state-of-the-art trained networks." @default.
• W1625958017 created "2016-06-24" @default.
• W1625958017 creator A5025218580 @default.
• W1625958017 creator A5025410418 @default.
• W1625958017 creator A5072571599 @default.
• W1625958017 date "2016-07-01" @default.
• W1625958017 modified "2023-10-17" @default.
• W1625958017 title "Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?" @default.
• W1625958017 cites W1606858007 @default.
• W1625958017 cites W1820849028 @default.
• W1625958017 cites W1915485278 @default.
• W1625958017 cites W1933990309 @default.
• W1625958017 cites W1971310220 @default.
• W1625958017 cites W1977601760 @default.
• W1625958017 cites W1984305442 @default.
• W1625958017 cites W1993717606 @default.
• W1625958017 cites W1993962865 @default.
• W1625958017 cites W2025223969 @default.
• W1625958017 cites W2068693086 @default.
• W1625958017 cites W2072072671 @default.
• W1625958017 cites W2076063813 @default.
• W1625958017 cites W2078397124 @default.
• W1625958017 cites W2098213359 @default.
• W1625958017 cites W2102129292 @default.
• W1625958017 cites W2102612409 @default.
• W1625958017 cites W2103496339 @default.
• W1625958017 cites W2113385666 @default.
• W1625958017 cites W2117539524 @default.
• W1625958017 cites W2121194215 @default.
• W1625958017 cites W2129638195 @default.
• W1625958017 cites W2134033146 @default.
• W1625958017 cites W2137825973 @default.
• W1625958017 cites W2137983211 @default.
• W1625958017 cites W2142947774 @default.
• W1625958017 cites W2144161366 @default.
• W1625958017 cites W2163922914 @default.
• W1625958017 cites W2167828456 @default.
• W1625958017 cites W2963173190 @default.
• W1625958017 cites W2963302510 @default.
• W1625958017 cites W2963607629 @default.
• W1625958017 cites W2964322027 @default.
• W1625958017 cites W2979473749 @default.
• W1625958017 cites W3124617746 @default.
• W1625958017 cites W4301425558 @default.
• W1625958017 cites W937846259 @default.
• W1625958017 doi "https://doi.org/10.1109/tsp.2016.2546221" @default.
• W1625958017 hasPublicationYear "2016" @default.
• W1625958017 type Work @default.
• W1625958017 sameAs 1625958017 @default.
• W1625958017 citedByCount "131" @default.
• W1625958017 countsByYear W16259580172014 @default.
• W1625958017 countsByYear W16259580172015 @default.
• W1625958017 countsByYear W16259580172016 @default.
• W1625958017 countsByYear W16259580172017 @default.
• W1625958017 countsByYear W16259580172018 @default.
• W1625958017 countsByYear W16259580172019 @default.
• W1625958017 countsByYear W16259580172020 @default.
• W1625958017 countsByYear W16259580172021 @default.
• W1625958017 countsByYear W16259580172022 @default.
• W1625958017 countsByYear W16259580172023 @default.
• W1625958017 crossrefType "journal-article" @default.
• W1625958017 hasAuthorship W1625958017A5025218580 @default.
• W1625958017 hasAuthorship W1625958017A5025410418 @default.
• W1625958017 hasAuthorship W1625958017A5072571599 @default.
• W1625958017 hasBestOaLocation W16259580171 @default.
• W1625958017 hasConcept C108583219 @default.
• W1625958017 hasConcept C119857082 @default.
• W1625958017 hasConcept C121332964 @default.
• W1625958017 hasConcept C124101348 @default.
• W1625958017 hasConcept C153180895 @default.
• W1625958017 hasConcept C154945302 @default.
• W1625958017 hasConcept C162324750 @default.
• W1625958017 hasConcept C163716315 @default.
• W1625958017 hasConcept C165696696 @default.
• W1625958017 hasConcept C176217482 @default.
• W1625958017 hasConcept C177264268 @default.
• W1625958017 hasConcept C199360897 @default.
• W1625958017 hasConcept C21547014 @default.
• W1625958017 hasConcept C25343380 @default.
• W1625958017 hasConcept C2777212361 @default.
• W1625958017 hasConcept C38652104 @default.
• W1625958017 hasConcept C41008148 @default.
• W1625958017 hasConcept C41608201 @default.
• W1625958017 hasConcept C50644808 @default.
• W1625958017 hasConcept C62520636 @default.
• W1625958017 hasConcept C80444323 @default.
• W1625958017 hasConceptScore W1625958017C108583219 @default.
• W1625958017 hasConceptScore W1625958017C119857082 @default.
• W1625958017 hasConceptScore W1625958017C121332964 @default.
• W1625958017 hasConceptScore W1625958017C124101348 @default.
• W1625958017 hasConceptScore W1625958017C153180895 @default.
• W1625958017 hasConceptScore W1625958017C154945302 @default.
• W1625958017 hasConceptScore W1625958017C162324750 @default.
• W1625958017 hasConceptScore W1625958017C163716315 @default.
• W1625958017 hasConceptScore W1625958017C165696696 @default.
• W1625958017 hasConceptScore W1625958017C176217482 @default.
• W1625958017 hasConceptScore W1625958017C177264268 @default.
• W1625958017 hasConceptScore W1625958017C199360897 @default.

• next