Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386966229> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4386966229 endingPage "110863" @default.
- W4386966229 startingPage "110863" @default.
- W4386966229 abstract "In this paper, we explore a deep learning feed-forward artificial neural network (ANN) framework as a numerical tool for the solution of singularly perturbed delay differential equations (SPDDE). Our approach trains the network with fewer number of uniform data points along with a linear interpolation as a dependent variable. More importantly, the exact solution is not used for training the network. A mean square or Euclidean norm type total loss function is utilized to assess the deep learning networks’ performance. In the training and testing phase, our network adjust itself to fit the tangent and the curvature by minimizing the total loss function and fine-tuning the network’s hyperparameters during the backpropogation stage. Our focus in this contribution is to investigate an answer to the question- “whether neural networks can learn to solve the differential equations with both delay and boundary layer behavior”? Traditional numerical methods known to perform poorly in approximating the solutions to SPDDE due to boundary layer behavior, which is the sharp change in the gradient of the solution inside a region of very small width. Our proposed network architecture is used to investigate the above question for three varieties of SPDDEs. The numerical results demonstrate that the fine-tuned adaptive deep learning architecture can effectively approximate the solution to SPDDEs for varieties of delay and perturbation parameter. It is expected that the current method can be extendable to approximate 2D convection–diffusion partial differential equations with boundary layer." @default.
- W4386966229 created "2023-09-23" @default.
- W4386966229 creator A5064671544 @default.
- W4386966229 date "2023-11-01" @default.
- W4386966229 modified "2023-10-16" @default.
- W4386966229 title "A deep learning feed-forward neural network framework for the solutions to singularly perturbed delay differential equations" @default.
- W4386966229 cites W1019830208 @default.
- W4386966229 cites W1126325483 @default.
- W4386966229 cites W1970346034 @default.
- W4386966229 cites W1978075626 @default.
- W4386966229 cites W2015881396 @default.
- W4386966229 cites W2018032381 @default.
- W4386966229 cites W2034650523 @default.
- W4386966229 cites W2040242941 @default.
- W4386966229 cites W2052798315 @default.
- W4386966229 cites W2054914575 @default.
- W4386966229 cites W2070206539 @default.
- W4386966229 cites W2075613575 @default.
- W4386966229 cites W2103496339 @default.
- W4386966229 cites W2137983211 @default.
- W4386966229 cites W2148666448 @default.
- W4386966229 cites W2194321275 @default.
- W4386966229 cites W2306570595 @default.
- W4386966229 cites W2911290743 @default.
- W4386966229 cites W2912149013 @default.
- W4386966229 cites W2912374992 @default.
- W4386966229 cites W2919115771 @default.
- W4386966229 cites W2970121961 @default.
- W4386966229 cites W2990346675 @default.
- W4386966229 cites W3101260193 @default.
- W4386966229 cites W3118554780 @default.
- W4386966229 cites W3164032021 @default.
- W4386966229 cites W3169046500 @default.
- W4386966229 cites W3172912024 @default.
- W4386966229 cites W67460923 @default.
- W4386966229 doi "https://doi.org/10.1016/j.asoc.2023.110863" @default.
- W4386966229 hasPublicationYear "2023" @default.
- W4386966229 type Work @default.
- W4386966229 citedByCount "0" @default.
- W4386966229 crossrefType "journal-article" @default.
- W4386966229 hasAuthorship W4386966229A5064671544 @default.
- W4386966229 hasConcept C108583219 @default.
- W4386966229 hasConcept C11413529 @default.
- W4386966229 hasConcept C126255220 @default.
- W4386966229 hasConcept C134306372 @default.
- W4386966229 hasConcept C147504518 @default.
- W4386966229 hasConcept C154945302 @default.
- W4386966229 hasConcept C28826006 @default.
- W4386966229 hasConcept C33923547 @default.
- W4386966229 hasConcept C41008148 @default.
- W4386966229 hasConcept C47702885 @default.
- W4386966229 hasConcept C50644808 @default.
- W4386966229 hasConcept C78045399 @default.
- W4386966229 hasConceptScore W4386966229C108583219 @default.
- W4386966229 hasConceptScore W4386966229C11413529 @default.
- W4386966229 hasConceptScore W4386966229C126255220 @default.
- W4386966229 hasConceptScore W4386966229C134306372 @default.
- W4386966229 hasConceptScore W4386966229C147504518 @default.
- W4386966229 hasConceptScore W4386966229C154945302 @default.
- W4386966229 hasConceptScore W4386966229C28826006 @default.
- W4386966229 hasConceptScore W4386966229C33923547 @default.
- W4386966229 hasConceptScore W4386966229C41008148 @default.
- W4386966229 hasConceptScore W4386966229C47702885 @default.
- W4386966229 hasConceptScore W4386966229C50644808 @default.
- W4386966229 hasConceptScore W4386966229C78045399 @default.
- W4386966229 hasFunder F4320310394 @default.
- W4386966229 hasLocation W43869662291 @default.
- W4386966229 hasOpenAccess W4386966229 @default.
- W4386966229 hasPrimaryLocation W43869662291 @default.
- W4386966229 hasRelatedWork W1261320338 @default.
- W4386966229 hasRelatedWork W1555995843 @default.
- W4386966229 hasRelatedWork W1595652908 @default.
- W4386966229 hasRelatedWork W1604847762 @default.
- W4386966229 hasRelatedWork W1675687971 @default.
- W4386966229 hasRelatedWork W2028903792 @default.
- W4386966229 hasRelatedWork W2357447513 @default.
- W4386966229 hasRelatedWork W2358123629 @default.
- W4386966229 hasRelatedWork W2378845890 @default.
- W4386966229 hasRelatedWork W3125716114 @default.
- W4386966229 hasVolume "148" @default.
- W4386966229 isParatext "false" @default.
- W4386966229 isRetracted "false" @default.
- W4386966229 workType "article" @default.