FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892911634> ?p ?o ?g. }

• W2892911634 endingPage "37" @default.
• W2892911634 startingPage "22" @default.
• W2892911634 abstract "A Deep Boltzmann Machine is a model of a Deep Neural Network formed from multiple layers of neurons with nonlinear activation functions. The structure of a Deep Boltzmann Machine enables it to learn very complex relationships between features and facilitates advanced performance in learning of high-level representation of features, compared to conventional Artificial Neural Networks. Feature selection at the input level of Deep Neural Networks has not been well studied, despite its importance in reducing the input features processed by the deep learning model, which facilitates understanding of the data. This paper proposes a novel algorithm, Deep Feature Selection (Deep-FS), which is capable of removing irrelevant features from large datasets in order to reduce the number of inputs which are modelled during the learning process. The proposed Deep-FS algorithm utilizes a Deep Boltzmann Machine, and uses knowledge which is acquired during training to remove features at the beginning of the learning process. Reducing inputs is important because it prevents the network from learning the associations between the irrelevant features which negatively impact on the acquired knowledge of the network about the overall distribution of the data. The Deep-FS method embeds feature selection in a Restricted Boltzmann Machine which is used for training a Deep Boltzmann Machine. The generative property of the Restricted Boltzmann Machine is used to reconstruct eliminated features and calculate reconstructed errors, in order to evaluate the impact of eliminating features. The performance of the proposed approach was evaluated with experiments conducted using the MNIST, MIR-Flickr, GISETTE, MADELON and PANCAN datasets. The results revealed that the proposed Deep-FS method enables improved feature selection without loss of accuracy on the MIR-Flickr dataset, where Deep-FS reduced the number of input features by removing 775 features without reduction in performance. With regards to the MNIST dataset, Deep-FS reduced the number of input features by more than 45%; it reduced the network error from 0.97% to 0.90%, and also reduced processing and classification time by more than 5.5%. Additionally, when compared to classical feature selection methods, Deep-FS returned higher accuracy. The experimental results on GISETTE, MADELON and PANCAN showed that Deep-FS reduced 81%, 57% and 77% of the number of input features, respectively. Moreover, the proposed feature selection method reduced the classifier training time by 82%, 70% and 85% on GISETTE, MADELON and PANCAN datasets, respectively. Experiments with various datasets, comprising a large number of features and samples, revealed that the proposed Deep-FS algorithm overcomes the main limitations of classical feature selection algorithms. More specifically, most classical methods require, as a prerequisite, a pre-specified number of features to retain, however in Deep-FS this number is identified automatically. Deep-FS performs the feature selection task faster than classical feature selection algorithms which makes it suitable for deep learning tasks. In addition, Deep-FS is suitable for finding features in large and big datasets which are normally stored in data batches for faster and more efficient processing." @default.
• W2892911634 created "2018-10-05" @default.
• W2892911634 creator A5022173527 @default.
• W2892911634 creator A5029315420 @default.
• W2892911634 creator A5057339312 @default.
• W2892911634 date "2018-12-01" @default.
• W2892911634 modified "2023-10-16" @default.
• W2892911634 title "Deep-FS: A feature selection algorithm for Deep Boltzmann Machines" @default.
• W2892911634 cites W1966659765 @default.
• W2892911634 cites W2018168021 @default.
• W2892911634 cites W2019779527 @default.
• W2892911634 cites W2073137089 @default.
• W2892911634 cites W2088338354 @default.
• W2892911634 cites W2100495367 @default.
• W2892911634 cites W2100717332 @default.
• W2892911634 cites W2112796928 @default.
• W2892911634 cites W2116064496 @default.
• W2892911634 cites W2119387367 @default.
• W2892911634 cites W2124537004 @default.
• W2892911634 cites W2136922672 @default.
• W2892911634 cites W2143062820 @default.
• W2892911634 cites W2143426320 @default.
• W2892911634 cites W2147768505 @default.
• W2892911634 cites W2154053567 @default.
• W2892911634 cites W2156758690 @default.
• W2892911634 cites W2158485828 @default.
• W2892911634 cites W2160815625 @default.
• W2892911634 cites W2167101736 @default.
• W2892911634 cites W2171145682 @default.
• W2892911634 cites W2253609413 @default.
• W2892911634 cites W2528158016 @default.
• W2892911634 cites W2582761306 @default.
• W2892911634 cites W4289236186 @default.
• W2892911634 doi "https://doi.org/10.1016/j.neucom.2018.09.040" @default.
• W2892911634 hasPublicationYear "2018" @default.
• W2892911634 type Work @default.
• W2892911634 sameAs 2892911634 @default.
• W2892911634 citedByCount "50" @default.
• W2892911634 countsByYear W28929116342019 @default.
• W2892911634 countsByYear W28929116342020 @default.
• W2892911634 countsByYear W28929116342021 @default.
• W2892911634 countsByYear W28929116342022 @default.
• W2892911634 countsByYear W28929116342023 @default.
• W2892911634 crossrefType "journal-article" @default.
• W2892911634 hasAuthorship W2892911634A5022173527 @default.
• W2892911634 hasAuthorship W2892911634A5029315420 @default.
• W2892911634 hasAuthorship W2892911634A5057339312 @default.
• W2892911634 hasBestOaLocation W28929116341 @default.
• W2892911634 hasConcept C108583219 @default.
• W2892911634 hasConcept C111919701 @default.
• W2892911634 hasConcept C11413529 @default.
• W2892911634 hasConcept C119857082 @default.
• W2892911634 hasConcept C138885662 @default.
• W2892911634 hasConcept C148483581 @default.
• W2892911634 hasConcept C153180895 @default.
• W2892911634 hasConcept C154945302 @default.
• W2892911634 hasConcept C190502265 @default.
• W2892911634 hasConcept C192576344 @default.
• W2892911634 hasConcept C199354608 @default.
• W2892911634 hasConcept C2776401178 @default.
• W2892911634 hasConcept C41008148 @default.
• W2892911634 hasConcept C41895202 @default.
• W2892911634 hasConcept C50644808 @default.
• W2892911634 hasConcept C97385483 @default.
• W2892911634 hasConcept C98045186 @default.
• W2892911634 hasConceptScore W2892911634C108583219 @default.
• W2892911634 hasConceptScore W2892911634C111919701 @default.
• W2892911634 hasConceptScore W2892911634C11413529 @default.
• W2892911634 hasConceptScore W2892911634C119857082 @default.
• W2892911634 hasConceptScore W2892911634C138885662 @default.
• W2892911634 hasConceptScore W2892911634C148483581 @default.
• W2892911634 hasConceptScore W2892911634C153180895 @default.
• W2892911634 hasConceptScore W2892911634C154945302 @default.
• W2892911634 hasConceptScore W2892911634C190502265 @default.
• W2892911634 hasConceptScore W2892911634C192576344 @default.
• W2892911634 hasConceptScore W2892911634C199354608 @default.
• W2892911634 hasConceptScore W2892911634C2776401178 @default.
• W2892911634 hasConceptScore W2892911634C41008148 @default.
• W2892911634 hasConceptScore W2892911634C41895202 @default.
• W2892911634 hasConceptScore W2892911634C50644808 @default.
• W2892911634 hasConceptScore W2892911634C97385483 @default.
• W2892911634 hasConceptScore W2892911634C98045186 @default.
• W2892911634 hasLocation W28929116341 @default.
• W2892911634 hasLocation W28929116342 @default.
• W2892911634 hasLocation W28929116343 @default.
• W2892911634 hasOpenAccess W2892911634 @default.
• W2892911634 hasPrimaryLocation W28929116341 @default.
• W2892911634 hasRelatedWork W2287713958 @default.
• W2892911634 hasRelatedWork W2567271240 @default.
• W2892911634 hasRelatedWork W2774529511 @default.
• W2892911634 hasRelatedWork W2810292802 @default.
• W2892911634 hasRelatedWork W2892911634 @default.
• W2892911634 hasRelatedWork W2955124940 @default.
• W2892911634 hasRelatedWork W2971852391 @default.
• W2892911634 hasRelatedWork W3082895349 @default.
• W2892911634 hasRelatedWork W3123344745 @default.
• W2892911634 hasRelatedWork W870929296 @default.
• W2892911634 hasVolume "322" @default.

• next