Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898077965> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2898077965 abstract "Recently deep learning based architectures have been widely deployed in many problems of artificial intelligence. Among deep learning models, Convolutional Neural Networks (CNN) have been reported in numerous successful applications such as object recognition, and natural language processing. The convolutional neural networks are trained by back-propagating the classification error using the Back-Propagation (BP) algorithm, which requires a large amount of data and slows the training process. To overcome these difficulties, a new fast and accurate approach based on Extreme Learning Machine (ELM) to train any convolutional neural network has been proposed. The developed framework (ELM-CNN) is based on the concept of auto-encoding to learn the convolutional filters with biases, by reconstructing the normalized input and the intercept term. In this paper, systematic comparison with traditional back-propagation based training method (BP-CNN) has been made with respect to two aspects qualitative and quantitative. The experimental results on the popular MNIST dataset show that the ELM-CNN algorithm achieves competitive results in terms of generalization performance and up to 16 times faster than the back-propagation based training of CNN." @default.
- W2898077965 created "2018-10-26" @default.
- W2898077965 creator A5037439501 @default.
- W2898077965 creator A5059595536 @default.
- W2898077965 creator A5072523018 @default.
- W2898077965 date "2018-07-01" @default.
- W2898077965 modified "2023-09-25" @default.
- W2898077965 title "Convolutional Neural Network Features Comparison Between Back-Propagation and Extreme Learning Machine" @default.
- W2898077965 cites W1849277567 @default.
- W2898077965 cites W1963882359 @default.
- W2898077965 cites W2026131661 @default.
- W2898077965 cites W2117539524 @default.
- W2898077965 cites W2141695047 @default.
- W2898077965 cites W2552496680 @default.
- W2898077965 cites W2560323025 @default.
- W2898077965 cites W2802042319 @default.
- W2898077965 doi "https://doi.org/10.23919/chicc.2018.8482876" @default.
- W2898077965 hasPublicationYear "2018" @default.
- W2898077965 type Work @default.
- W2898077965 sameAs 2898077965 @default.
- W2898077965 citedByCount "5" @default.
- W2898077965 countsByYear W28980779652021 @default.
- W2898077965 countsByYear W28980779652022 @default.
- W2898077965 crossrefType "proceedings-article" @default.
- W2898077965 hasAuthorship W2898077965A5037439501 @default.
- W2898077965 hasAuthorship W2898077965A5059595536 @default.
- W2898077965 hasAuthorship W2898077965A5072523018 @default.
- W2898077965 hasConcept C108583219 @default.
- W2898077965 hasConcept C119857082 @default.
- W2898077965 hasConcept C134306372 @default.
- W2898077965 hasConcept C153180895 @default.
- W2898077965 hasConcept C154945302 @default.
- W2898077965 hasConcept C155032097 @default.
- W2898077965 hasConcept C177148314 @default.
- W2898077965 hasConcept C190502265 @default.
- W2898077965 hasConcept C2780150128 @default.
- W2898077965 hasConcept C33923547 @default.
- W2898077965 hasConcept C41008148 @default.
- W2898077965 hasConcept C50644808 @default.
- W2898077965 hasConcept C81363708 @default.
- W2898077965 hasConceptScore W2898077965C108583219 @default.
- W2898077965 hasConceptScore W2898077965C119857082 @default.
- W2898077965 hasConceptScore W2898077965C134306372 @default.
- W2898077965 hasConceptScore W2898077965C153180895 @default.
- W2898077965 hasConceptScore W2898077965C154945302 @default.
- W2898077965 hasConceptScore W2898077965C155032097 @default.
- W2898077965 hasConceptScore W2898077965C177148314 @default.
- W2898077965 hasConceptScore W2898077965C190502265 @default.
- W2898077965 hasConceptScore W2898077965C2780150128 @default.
- W2898077965 hasConceptScore W2898077965C33923547 @default.
- W2898077965 hasConceptScore W2898077965C41008148 @default.
- W2898077965 hasConceptScore W2898077965C50644808 @default.
- W2898077965 hasConceptScore W2898077965C81363708 @default.
- W2898077965 hasLocation W28980779651 @default.
- W2898077965 hasOpenAccess W2898077965 @default.
- W2898077965 hasPrimaryLocation W28980779651 @default.
- W2898077965 hasRelatedWork W2597787948 @default.
- W2898077965 hasRelatedWork W2731899572 @default.
- W2898077965 hasRelatedWork W2946016983 @default.
- W2898077965 hasRelatedWork W2947175736 @default.
- W2898077965 hasRelatedWork W3133861977 @default.
- W2898077965 hasRelatedWork W3156786002 @default.
- W2898077965 hasRelatedWork W3208266890 @default.
- W2898077965 hasRelatedWork W4309224979 @default.
- W2898077965 hasRelatedWork W4312417841 @default.
- W2898077965 hasRelatedWork W4321369474 @default.
- W2898077965 isParatext "false" @default.
- W2898077965 isRetracted "false" @default.
- W2898077965 magId "2898077965" @default.
- W2898077965 workType "article" @default.