Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892036170> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2892036170 abstract "This tutorial material on Convolutional Neural Networks (CNN) and its applications in digital media research is based on the concept of Symbolic Tensor Neural Networks. The set of STNN expressions is specified in Backus-Naur Form (BNF) which is annotated by constraints typical for labeled acyclic directed graphs (DAG). The BNF induction begins from a collection of neural unit symbols with extra (up to five) decoration fields (including tensor depth and sharing fields). The inductive rules provide not only the general graph structure but also the specific shortcuts for residual blocks of units. A syntactic mechanism for network fragments modularization is introduced via user defined units and their instances. Moreover, the dual BNF rules are specified in order to generate the Dual Symbolic Tensor Neural Network (DSTNN). The joined interpretation of STNN and DSTNN provides the correct flow of gradient tensors, back propagated at the training stage. The proposed symbolic representation of CNNs is illustrated for six generic digital media applications (CREAMS): Compression, Recognition, Embedding, Annotation, 3D Modeling for human-computer interfacing, and data Security based on digital media objects. In order to make the CNN description and its gradient flow complete, for all presented applications, the symbolic representations of mathematically defined loss/gain functions and gradient flow equations for all used core units, are given. The tutorial is to convince the reader that STNN is not only a convenient symbolic notation for public presentations of CNN based solutions for CREAMS problems but also that it is a design blueprint with a potential for automatic generation of application source code." @default.
- W2892036170 created "2018-09-27" @default.
- W2892036170 creator A5090710349 @default.
- W2892036170 date "2018-09-18" @default.
- W2892036170 modified "2023-09-27" @default.
- W2892036170 title "Symbolic Tensor Neural Networks for Digital Media - from Tensor Processing via BNF Graph Rules to CREAMS Applications" @default.
- W2892036170 cites W1498436455 @default.
- W2892036170 cites W1580389772 @default.
- W2892036170 cites W1686810756 @default.
- W2892036170 cites W20283819 @default.
- W2892036170 cites W2099471712 @default.
- W2892036170 cites W2173520492 @default.
- W2892036170 cites W2331128040 @default.
- W2892036170 cites W2502312327 @default.
- W2892036170 cites W2523246573 @default.
- W2892036170 cites W2774625825 @default.
- W2892036170 cites W2808631503 @default.
- W2892036170 cites W2894554753 @default.
- W2892036170 cites W2899771611 @default.
- W2892036170 cites W2950179405 @default.
- W2892036170 cites W2962793481 @default.
- W2892036170 cites W2963073614 @default.
- W2892036170 cites W2964121744 @default.
- W2892036170 hasPublicationYear "2018" @default.
- W2892036170 type Work @default.
- W2892036170 sameAs 2892036170 @default.
- W2892036170 citedByCount "1" @default.
- W2892036170 countsByYear W28920361702019 @default.
- W2892036170 crossrefType "posted-content" @default.
- W2892036170 hasAuthorship W2892036170A5090710349 @default.
- W2892036170 hasConcept C11413529 @default.
- W2892036170 hasConcept C133512626 @default.
- W2892036170 hasConcept C154945302 @default.
- W2892036170 hasConcept C155281189 @default.
- W2892036170 hasConcept C202444582 @default.
- W2892036170 hasConcept C33923547 @default.
- W2892036170 hasConcept C41008148 @default.
- W2892036170 hasConcept C41608201 @default.
- W2892036170 hasConcept C45374587 @default.
- W2892036170 hasConcept C50644808 @default.
- W2892036170 hasConcept C80444323 @default.
- W2892036170 hasConceptScore W2892036170C11413529 @default.
- W2892036170 hasConceptScore W2892036170C133512626 @default.
- W2892036170 hasConceptScore W2892036170C154945302 @default.
- W2892036170 hasConceptScore W2892036170C155281189 @default.
- W2892036170 hasConceptScore W2892036170C202444582 @default.
- W2892036170 hasConceptScore W2892036170C33923547 @default.
- W2892036170 hasConceptScore W2892036170C41008148 @default.
- W2892036170 hasConceptScore W2892036170C41608201 @default.
- W2892036170 hasConceptScore W2892036170C45374587 @default.
- W2892036170 hasConceptScore W2892036170C50644808 @default.
- W2892036170 hasConceptScore W2892036170C80444323 @default.
- W2892036170 hasLocation W28920361701 @default.
- W2892036170 hasOpenAccess W2892036170 @default.
- W2892036170 hasPrimaryLocation W28920361701 @default.
- W2892036170 hasRelatedWork W132697094 @default.
- W2892036170 hasRelatedWork W138953331 @default.
- W2892036170 hasRelatedWork W1518070129 @default.
- W2892036170 hasRelatedWork W1571253549 @default.
- W2892036170 hasRelatedWork W1573647137 @default.
- W2892036170 hasRelatedWork W198926601 @default.
- W2892036170 hasRelatedWork W1989507555 @default.
- W2892036170 hasRelatedWork W2246353450 @default.
- W2892036170 hasRelatedWork W2294984090 @default.
- W2892036170 hasRelatedWork W2396855650 @default.
- W2892036170 hasRelatedWork W2694490038 @default.
- W2892036170 hasRelatedWork W2761671779 @default.
- W2892036170 hasRelatedWork W2804522598 @default.
- W2892036170 hasRelatedWork W2914268814 @default.
- W2892036170 hasRelatedWork W2964022412 @default.
- W2892036170 hasRelatedWork W2975251625 @default.
- W2892036170 hasRelatedWork W3003579141 @default.
- W2892036170 hasRelatedWork W311328313 @default.
- W2892036170 hasRelatedWork W3186180380 @default.
- W2892036170 hasRelatedWork W2615614863 @default.
- W2892036170 isParatext "false" @default.
- W2892036170 isRetracted "false" @default.
- W2892036170 magId "2892036170" @default.
- W2892036170 workType "article" @default.