Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226164963> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4226164963 abstract "The deep learning algorithm called convolutional neural network (CNN) particularly with Residual Network (ResNet) receiving much attention from the research community in facial recognition recently. Unfortunately, the complexity of optimization problems in overfitting and vanishing gradient cause huge obstacles. More specifically, once the gradient is backpropagated in initial layers, repeated multiplication among layers constructs gradient infinitely small and causes the layers of the network to become deeper and degrade the performance. Moreover, the skip connection that comprises the residual network (ResNet) is not enough to solve the above-mentioned limitations, and this could downgrade the optimization of used layers and potentially further downgrade the accuracy. Therefore, a deep residual network (ResNet) with hybridized function i.e., convolutional-2D and Batch Norm is proposed as this could allow direct signal propagation from the initial to the final layer of the network for every single residual block deeply. Initially, the convolutional-2D and Batch Norm were constructed to overcome bias in-depth nets and propagate the gradients directly from the loss layers to any previous layers, while skipping intermediate weight layers deeply that have the potential to trigger vanishing or deterioration of the gradient signal. The proposed learning model has improved the degradation of accuracy drawback by decreasing the number of layers needed more in low level as compared to existing work for each block using batch normalization and convolutional-2D function." @default.
- W4226164963 created "2022-05-05" @default.
- W4226164963 creator A5009222548 @default.
- W4226164963 creator A5044459115 @default.
- W4226164963 creator A5048149984 @default.
- W4226164963 creator A5060469833 @default.
- W4226164963 creator A5066444368 @default.
- W4226164963 date "2021-12-22" @default.
- W4226164963 modified "2023-09-23" @default.
- W4226164963 title "An Emotion and Gender Detection Using Hybridized Convolutional 2D and Batch Norm Residual Network Learning" @default.
- W4226164963 cites W1905153633 @default.
- W4226164963 cites W1997566808 @default.
- W4226164963 cites W2116360511 @default.
- W4226164963 cites W2147768505 @default.
- W4226164963 cites W2510001427 @default.
- W4226164963 cites W2618530766 @default.
- W4226164963 cites W2805194238 @default.
- W4226164963 cites W2807068017 @default.
- W4226164963 cites W2919358988 @default.
- W4226164963 cites W2921811193 @default.
- W4226164963 cites W3131777259 @default.
- W4226164963 cites W3148865874 @default.
- W4226164963 cites W3167786448 @default.
- W4226164963 doi "https://doi.org/10.1145/3512576.3512590" @default.
- W4226164963 hasPublicationYear "2021" @default.
- W4226164963 type Work @default.
- W4226164963 citedByCount "0" @default.
- W4226164963 crossrefType "proceedings-article" @default.
- W4226164963 hasAuthorship W4226164963A5009222548 @default.
- W4226164963 hasAuthorship W4226164963A5044459115 @default.
- W4226164963 hasAuthorship W4226164963A5048149984 @default.
- W4226164963 hasAuthorship W4226164963A5060469833 @default.
- W4226164963 hasAuthorship W4226164963A5066444368 @default.
- W4226164963 hasConcept C108583219 @default.
- W4226164963 hasConcept C11413529 @default.
- W4226164963 hasConcept C126255220 @default.
- W4226164963 hasConcept C136886441 @default.
- W4226164963 hasConcept C144024400 @default.
- W4226164963 hasConcept C153180895 @default.
- W4226164963 hasConcept C154945302 @default.
- W4226164963 hasConcept C155512373 @default.
- W4226164963 hasConcept C17744445 @default.
- W4226164963 hasConcept C19165224 @default.
- W4226164963 hasConcept C191795146 @default.
- W4226164963 hasConcept C199539241 @default.
- W4226164963 hasConcept C22019652 @default.
- W4226164963 hasConcept C2779628075 @default.
- W4226164963 hasConcept C2944601119 @default.
- W4226164963 hasConcept C33923547 @default.
- W4226164963 hasConcept C38365724 @default.
- W4226164963 hasConcept C38652104 @default.
- W4226164963 hasConcept C41008148 @default.
- W4226164963 hasConcept C50644808 @default.
- W4226164963 hasConcept C81363708 @default.
- W4226164963 hasConceptScore W4226164963C108583219 @default.
- W4226164963 hasConceptScore W4226164963C11413529 @default.
- W4226164963 hasConceptScore W4226164963C126255220 @default.
- W4226164963 hasConceptScore W4226164963C136886441 @default.
- W4226164963 hasConceptScore W4226164963C144024400 @default.
- W4226164963 hasConceptScore W4226164963C153180895 @default.
- W4226164963 hasConceptScore W4226164963C154945302 @default.
- W4226164963 hasConceptScore W4226164963C155512373 @default.
- W4226164963 hasConceptScore W4226164963C17744445 @default.
- W4226164963 hasConceptScore W4226164963C19165224 @default.
- W4226164963 hasConceptScore W4226164963C191795146 @default.
- W4226164963 hasConceptScore W4226164963C199539241 @default.
- W4226164963 hasConceptScore W4226164963C22019652 @default.
- W4226164963 hasConceptScore W4226164963C2779628075 @default.
- W4226164963 hasConceptScore W4226164963C2944601119 @default.
- W4226164963 hasConceptScore W4226164963C33923547 @default.
- W4226164963 hasConceptScore W4226164963C38365724 @default.
- W4226164963 hasConceptScore W4226164963C38652104 @default.
- W4226164963 hasConceptScore W4226164963C41008148 @default.
- W4226164963 hasConceptScore W4226164963C50644808 @default.
- W4226164963 hasConceptScore W4226164963C81363708 @default.
- W4226164963 hasLocation W42261649631 @default.
- W4226164963 hasOpenAccess W4226164963 @default.
- W4226164963 hasPrimaryLocation W42261649631 @default.
- W4226164963 hasRelatedWork W2563602643 @default.
- W4226164963 hasRelatedWork W2893345206 @default.
- W4226164963 hasRelatedWork W2997709384 @default.
- W4226164963 hasRelatedWork W3012393889 @default.
- W4226164963 hasRelatedWork W3089733734 @default.
- W4226164963 hasRelatedWork W3121671597 @default.
- W4226164963 hasRelatedWork W4220996320 @default.
- W4226164963 hasRelatedWork W4283701629 @default.
- W4226164963 hasRelatedWork W4309224979 @default.
- W4226164963 hasRelatedWork W4313289428 @default.
- W4226164963 isParatext "false" @default.
- W4226164963 isRetracted "false" @default.
- W4226164963 workType "article" @default.