Matches in SemOpenAlex for { <https://semopenalex.org/work/W2355765288> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2355765288 abstract "We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity." @default.
- W2355765288 created "2016-06-24" @default.
- W2355765288 creator A5000103239 @default.
- W2355765288 creator A5007681565 @default.
- W2355765288 creator A5012300352 @default.
- W2355765288 creator A5022141765 @default.
- W2355765288 creator A5058839665 @default.
- W2355765288 creator A5073341246 @default.
- W2355765288 creator A5082521701 @default.
- W2355765288 date "2016-05-09" @default.
- W2355765288 modified "2023-09-27" @default.
- W2355765288 title "A Theoretical Analysis of Deep Neural Networks for Texture Classification" @default.
- W2355765288 cites W1560641100 @default.
- W2355765288 cites W1672197616 @default.
- W2355765288 cites W2029538739 @default.
- W2355765288 cites W2044465660 @default.
- W2355765288 cites W2089947415 @default.
- W2355765288 cites W2112796928 @default.
- W2355765288 cites W2136922672 @default.
- W2355765288 cites W2144242878 @default.
- W2355765288 cites W2157169955 @default.
- W2355765288 cites W2165533158 @default.
- W2355765288 cites W2211843587 @default.
- W2355765288 cites W2235604683 @default.
- W2355765288 cites W2496126447 @default.
- W2355765288 cites W3118608800 @default.
- W2355765288 cites W51946390 @default.
- W2355765288 cites W73877600 @default.
- W2355765288 hasPublicationYear "2016" @default.
- W2355765288 type Work @default.
- W2355765288 sameAs 2355765288 @default.
- W2355765288 citedByCount "1" @default.
- W2355765288 countsByYear W23557652882017 @default.
- W2355765288 crossrefType "posted-content" @default.
- W2355765288 hasAuthorship W2355765288A5000103239 @default.
- W2355765288 hasAuthorship W2355765288A5007681565 @default.
- W2355765288 hasAuthorship W2355765288A5012300352 @default.
- W2355765288 hasAuthorship W2355765288A5022141765 @default.
- W2355765288 hasAuthorship W2355765288A5058839665 @default.
- W2355765288 hasAuthorship W2355765288A5073341246 @default.
- W2355765288 hasAuthorship W2355765288A5082521701 @default.
- W2355765288 hasConcept C111030470 @default.
- W2355765288 hasConcept C114614502 @default.
- W2355765288 hasConcept C146599234 @default.
- W2355765288 hasConcept C153180895 @default.
- W2355765288 hasConcept C154945302 @default.
- W2355765288 hasConcept C30732413 @default.
- W2355765288 hasConcept C33676613 @default.
- W2355765288 hasConcept C33923547 @default.
- W2355765288 hasConcept C41008148 @default.
- W2355765288 hasConcept C50644808 @default.
- W2355765288 hasConcept C81363708 @default.
- W2355765288 hasConcept C83665646 @default.
- W2355765288 hasConcept C97931131 @default.
- W2355765288 hasConceptScore W2355765288C111030470 @default.
- W2355765288 hasConceptScore W2355765288C114614502 @default.
- W2355765288 hasConceptScore W2355765288C146599234 @default.
- W2355765288 hasConceptScore W2355765288C153180895 @default.
- W2355765288 hasConceptScore W2355765288C154945302 @default.
- W2355765288 hasConceptScore W2355765288C30732413 @default.
- W2355765288 hasConceptScore W2355765288C33676613 @default.
- W2355765288 hasConceptScore W2355765288C33923547 @default.
- W2355765288 hasConceptScore W2355765288C41008148 @default.
- W2355765288 hasConceptScore W2355765288C50644808 @default.
- W2355765288 hasConceptScore W2355765288C81363708 @default.
- W2355765288 hasConceptScore W2355765288C83665646 @default.
- W2355765288 hasConceptScore W2355765288C97931131 @default.
- W2355765288 hasLocation W23557652881 @default.
- W2355765288 hasOpenAccess W2355765288 @default.
- W2355765288 hasPrimaryLocation W23557652881 @default.
- W2355765288 hasRelatedWork W1601292208 @default.
- W2355765288 hasRelatedWork W1835123606 @default.
- W2355765288 hasRelatedWork W2055346081 @default.
- W2355765288 hasRelatedWork W2063064098 @default.
- W2355765288 hasRelatedWork W2102852560 @default.
- W2355765288 hasRelatedWork W2113477426 @default.
- W2355765288 hasRelatedWork W2113498043 @default.
- W2355765288 hasRelatedWork W2121380873 @default.
- W2355765288 hasRelatedWork W2204975001 @default.
- W2355765288 hasRelatedWork W2578369184 @default.
- W2355765288 hasRelatedWork W2783359318 @default.
- W2355765288 hasRelatedWork W2896124229 @default.
- W2355765288 hasRelatedWork W2963234238 @default.
- W2355765288 hasRelatedWork W2999184797 @default.
- W2355765288 hasRelatedWork W3015475128 @default.
- W2355765288 hasRelatedWork W3177324614 @default.
- W2355765288 hasRelatedWork W3202619440 @default.
- W2355765288 hasRelatedWork W585462335 @default.
- W2355765288 hasRelatedWork W2833435207 @default.
- W2355765288 hasRelatedWork W3019281874 @default.
- W2355765288 isParatext "false" @default.
- W2355765288 isRetracted "false" @default.
- W2355765288 magId "2355765288" @default.
- W2355765288 workType "article" @default.