Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200302816> ?p ?o ?g. }
- W4200302816 endingPage "11" @default.
- W4200302816 startingPage "11" @default.
- W4200302816 abstract "Convolutional neural networks (CNNs) have powerful representation learning capabilities by automatically learning and extracting features directly from inputs. In classification applications, CNN models are typically composed of: convolutional layers, pooling layers, and fully connected (FC) layer(s). In a chain-based deep neural network, the FC layers contain most of the parameters of the network, which affects memory occupancy and computational complexity. For many real-world problems, speeding up inference time is an important matter because of the hardware design implications. To deal with this problem, we propose the replacement of the FC layers with a Hopfield neural network (HNN). The proposed architecture combines both a CNN and an HNN: A pretrained CNN model is used for feature extraction, followed by an HNN, which is considered as an associative memory that saves all features created by the CNN. Then, to deal with the limitation of the storage capacity of the HNN, the proposed work uses multiple HNNs. To optimize this step, the knapsack problem formulation is proposed, and a genetic algorithm (GA) is used solve it. According to the results obtained on the Noisy MNIST Dataset, our work outperformed the state-of-the-art algorithms." @default.
- W4200302816 created "2021-12-31" @default.
- W4200302816 creator A5007306111 @default.
- W4200302816 creator A5067068847 @default.
- W4200302816 date "2021-12-27" @default.
- W4200302816 modified "2023-10-16" @default.
- W4200302816 title "Optimal CNN–Hopfield Network for Pattern Recognition Based on a Genetic Algorithm" @default.
- W4200302816 cites W1507589574 @default.
- W4200302816 cites W1586409345 @default.
- W4200302816 cites W1597286183 @default.
- W4200302816 cites W1965496542 @default.
- W4200302816 cites W1984431842 @default.
- W4200302816 cites W2009443800 @default.
- W4200302816 cites W2011332780 @default.
- W4200302816 cites W2059146732 @default.
- W4200302816 cites W2059988607 @default.
- W4200302816 cites W2071128523 @default.
- W4200302816 cites W2072767449 @default.
- W4200302816 cites W2102184039 @default.
- W4200302816 cites W2110163023 @default.
- W4200302816 cites W2112796928 @default.
- W4200302816 cites W2121092885 @default.
- W4200302816 cites W2243370844 @default.
- W4200302816 cites W2402292288 @default.
- W4200302816 cites W2497122656 @default.
- W4200302816 cites W2500751094 @default.
- W4200302816 cites W2567001798 @default.
- W4200302816 cites W2601707599 @default.
- W4200302816 cites W2618530766 @default.
- W4200302816 cites W2800452261 @default.
- W4200302816 cites W2887063112 @default.
- W4200302816 cites W2887286714 @default.
- W4200302816 cites W2913292019 @default.
- W4200302816 cites W2963588253 @default.
- W4200302816 cites W2996367417 @default.
- W4200302816 cites W3021613070 @default.
- W4200302816 cites W3102889924 @default.
- W4200302816 cites W3105463048 @default.
- W4200302816 cites W3159908420 @default.
- W4200302816 cites W3176909558 @default.
- W4200302816 cites W4214871172 @default.
- W4200302816 cites W639708223 @default.
- W4200302816 doi "https://doi.org/10.3390/a15010011" @default.
- W4200302816 hasPublicationYear "2021" @default.
- W4200302816 type Work @default.
- W4200302816 citedByCount "3" @default.
- W4200302816 countsByYear W42003028162022 @default.
- W4200302816 countsByYear W42003028162023 @default.
- W4200302816 crossrefType "journal-article" @default.
- W4200302816 hasAuthorship W4200302816A5007306111 @default.
- W4200302816 hasAuthorship W4200302816A5067068847 @default.
- W4200302816 hasBestOaLocation W42003028161 @default.
- W4200302816 hasConcept C113138325 @default.
- W4200302816 hasConcept C11413529 @default.
- W4200302816 hasConcept C119857082 @default.
- W4200302816 hasConcept C138885662 @default.
- W4200302816 hasConcept C153180895 @default.
- W4200302816 hasConcept C154945302 @default.
- W4200302816 hasConcept C190502265 @default.
- W4200302816 hasConcept C2776214188 @default.
- W4200302816 hasConcept C2776401178 @default.
- W4200302816 hasConcept C41008148 @default.
- W4200302816 hasConcept C41895202 @default.
- W4200302816 hasConcept C50644808 @default.
- W4200302816 hasConcept C53442348 @default.
- W4200302816 hasConcept C70437156 @default.
- W4200302816 hasConcept C81363708 @default.
- W4200302816 hasConcept C8880873 @default.
- W4200302816 hasConceptScore W4200302816C113138325 @default.
- W4200302816 hasConceptScore W4200302816C11413529 @default.
- W4200302816 hasConceptScore W4200302816C119857082 @default.
- W4200302816 hasConceptScore W4200302816C138885662 @default.
- W4200302816 hasConceptScore W4200302816C153180895 @default.
- W4200302816 hasConceptScore W4200302816C154945302 @default.
- W4200302816 hasConceptScore W4200302816C190502265 @default.
- W4200302816 hasConceptScore W4200302816C2776214188 @default.
- W4200302816 hasConceptScore W4200302816C2776401178 @default.
- W4200302816 hasConceptScore W4200302816C41008148 @default.
- W4200302816 hasConceptScore W4200302816C41895202 @default.
- W4200302816 hasConceptScore W4200302816C50644808 @default.
- W4200302816 hasConceptScore W4200302816C53442348 @default.
- W4200302816 hasConceptScore W4200302816C70437156 @default.
- W4200302816 hasConceptScore W4200302816C81363708 @default.
- W4200302816 hasConceptScore W4200302816C8880873 @default.
- W4200302816 hasIssue "1" @default.
- W4200302816 hasLocation W42003028161 @default.
- W4200302816 hasLocation W42003028162 @default.
- W4200302816 hasOpenAccess W4200302816 @default.
- W4200302816 hasPrimaryLocation W42003028161 @default.
- W4200302816 hasRelatedWork W2554869829 @default.
- W4200302816 hasRelatedWork W2758063741 @default.
- W4200302816 hasRelatedWork W2760085659 @default.
- W4200302816 hasRelatedWork W2792873414 @default.
- W4200302816 hasRelatedWork W2901435809 @default.
- W4200302816 hasRelatedWork W2908808515 @default.
- W4200302816 hasRelatedWork W2913749182 @default.
- W4200302816 hasRelatedWork W2940661641 @default.
- W4200302816 hasRelatedWork W3156786002 @default.