Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890160131> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2890160131 abstract "Deep convolutional neural network (DCNN) is a powerful model for learning significant data at multiple levels of abstraction form an input image. However, training DCNN is often complicated because of parameter initialization, overfitting and convergence problems. Hence this work has been targeted to overcome the challenges of training DCNN with an optimized model. This chapter describes a deep learning framework for image classification with cifar-10 dataset. The model contains a set of convolutional layers with rectified linear unit activation function, max-pooling layers, and a fully-connected layer with softmax activation function. This model learns the features automatically and classifies the image without using the hand-crafted image based features. In this investigation, various optimizers have been applied in gradient descent technique for minimizing the loss function. Model with Adam optimizer constantly minimizes the objective function compared with other standard optimizers such as momentum, Rmsprop, and Adadelta. Dropout and batch normalization techniques are adapted to improve the model performance further by avoiding overfitting. Dropout function deactivates the insignificant node form the model after every epoch. The initialization of a large number of parameters in DCNN is regularized by batch normalization. Results obtained from the proposed model shows that batch normalization with dropout significantly improves the accuracy of the model with the tradeoff of computational complexity." @default.
- W2890160131 created "2018-09-27" @default.
- W2890160131 creator A5018052220 @default.
- W2890160131 creator A5084221842 @default.
- W2890160131 date "2018-09-20" @default.
- W2890160131 modified "2023-09-27" @default.
- W2890160131 title "Analyzing the Effect of Optimization Strategies in Deep Convolutional Neural Network" @default.
- W2890160131 cites W2097117768 @default.
- W2890160131 cites W2107878631 @default.
- W2890160131 cites W2112796928 @default.
- W2890160131 cites W2136922672 @default.
- W2890160131 cites W2331143823 @default.
- W2890160131 cites W2417429787 @default.
- W2890160131 cites W2463839664 @default.
- W2890160131 cites W2603747177 @default.
- W2890160131 cites W2735666957 @default.
- W2890160131 cites W2747705082 @default.
- W2890160131 cites W2758007480 @default.
- W2890160131 cites W2772452219 @default.
- W2890160131 cites W2785673949 @default.
- W2890160131 cites W2919115771 @default.
- W2890160131 cites W2964137095 @default.
- W2890160131 cites W321240543 @default.
- W2890160131 cites W4205947740 @default.
- W2890160131 doi "https://doi.org/10.1007/978-3-319-96002-9_10" @default.
- W2890160131 hasPublicationYear "2018" @default.
- W2890160131 type Work @default.
- W2890160131 sameAs 2890160131 @default.
- W2890160131 citedByCount "2" @default.
- W2890160131 countsByYear W28901601312020 @default.
- W2890160131 countsByYear W28901601312021 @default.
- W2890160131 crossrefType "book-chapter" @default.
- W2890160131 hasAuthorship W2890160131A5018052220 @default.
- W2890160131 hasAuthorship W2890160131A5084221842 @default.
- W2890160131 hasConcept C108583219 @default.
- W2890160131 hasConcept C114466953 @default.
- W2890160131 hasConcept C115961682 @default.
- W2890160131 hasConcept C119857082 @default.
- W2890160131 hasConcept C136886441 @default.
- W2890160131 hasConcept C144024400 @default.
- W2890160131 hasConcept C153180895 @default.
- W2890160131 hasConcept C154945302 @default.
- W2890160131 hasConcept C188441871 @default.
- W2890160131 hasConcept C19165224 @default.
- W2890160131 hasConcept C199360897 @default.
- W2890160131 hasConcept C22019652 @default.
- W2890160131 hasConcept C2776145597 @default.
- W2890160131 hasConcept C2778049539 @default.
- W2890160131 hasConcept C38365724 @default.
- W2890160131 hasConcept C41008148 @default.
- W2890160131 hasConcept C50644808 @default.
- W2890160131 hasConcept C75294576 @default.
- W2890160131 hasConcept C81363708 @default.
- W2890160131 hasConceptScore W2890160131C108583219 @default.
- W2890160131 hasConceptScore W2890160131C114466953 @default.
- W2890160131 hasConceptScore W2890160131C115961682 @default.
- W2890160131 hasConceptScore W2890160131C119857082 @default.
- W2890160131 hasConceptScore W2890160131C136886441 @default.
- W2890160131 hasConceptScore W2890160131C144024400 @default.
- W2890160131 hasConceptScore W2890160131C153180895 @default.
- W2890160131 hasConceptScore W2890160131C154945302 @default.
- W2890160131 hasConceptScore W2890160131C188441871 @default.
- W2890160131 hasConceptScore W2890160131C19165224 @default.
- W2890160131 hasConceptScore W2890160131C199360897 @default.
- W2890160131 hasConceptScore W2890160131C22019652 @default.
- W2890160131 hasConceptScore W2890160131C2776145597 @default.
- W2890160131 hasConceptScore W2890160131C2778049539 @default.
- W2890160131 hasConceptScore W2890160131C38365724 @default.
- W2890160131 hasConceptScore W2890160131C41008148 @default.
- W2890160131 hasConceptScore W2890160131C50644808 @default.
- W2890160131 hasConceptScore W2890160131C75294576 @default.
- W2890160131 hasConceptScore W2890160131C81363708 @default.
- W2890160131 hasLocation W28901601311 @default.
- W2890160131 hasOpenAccess W2890160131 @default.
- W2890160131 hasPrimaryLocation W28901601311 @default.
- W2890160131 hasRelatedWork W2760944304 @default.
- W2890160131 hasRelatedWork W2766123424 @default.
- W2890160131 hasRelatedWork W2767651786 @default.
- W2890160131 hasRelatedWork W2890160131 @default.
- W2890160131 hasRelatedWork W2940447366 @default.
- W2890160131 hasRelatedWork W2988779632 @default.
- W2890160131 hasRelatedWork W3154289258 @default.
- W2890160131 hasRelatedWork W3162092403 @default.
- W2890160131 hasRelatedWork W3186919929 @default.
- W2890160131 hasRelatedWork W4225996392 @default.
- W2890160131 isParatext "false" @default.
- W2890160131 isRetracted "false" @default.
- W2890160131 magId "2890160131" @default.
- W2890160131 workType "book-chapter" @default.