FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138129969> ?p ?o ?g. }

• W3138129969 abstract "The brain, as the source of inspiration for Artificial Neural Networks (ANN), is based on a sparse structure. This sparse structure helps the brain to consume less energy, learn easier and generalize patterns better than any other ANN. In this paper, two evolutionary methods for adopting sparsity to ANNs are proposed. In the proposed methods, the sparse structure of a network as well as the values of its parameters are trained and updated during the learning process. The simulation results show that these two methods have better accuracy and faster convergence while they need fewer training samples compared to their sparse and non-sparse counterparts. Furthermore, the proposed methods significantly improve the generalization power and reduce the number of parameters. For example, the sparsification of the ResNet47 network by exploiting our proposed methods for the image classification of ImageNet dataset uses 40 % fewer parameters while the top-1 accuracy of the model improves by 12% and 5% compared to the dense network and their sparse counterpart, respectively. As another example, the proposed methods for the CIFAR10 dataset converge to their final structure 7 times faster than its sparse counterpart, while the final accuracy increases by 6%." @default.
• W3138129969 created "2021-03-29" @default.
• W3138129969 creator A5007627998 @default.
• W3138129969 creator A5064119706 @default.
• W3138129969 creator A5069159448 @default.
• W3138129969 date "2021-03-13" @default.
• W3138129969 modified "2023-09-27" @default.
• W3138129969 title "Efficient Sparse Artificial Neural Networks." @default.
• W3138129969 cites W1552141811 @default.
• W3138129969 cites W1586554382 @default.
• W3138129969 cites W1665214252 @default.
• W3138129969 cites W1853900790 @default.
• W3138129969 cites W1904365287 @default.
• W3138129969 cites W1999653836 @default.
• W3138129969 cites W2008620264 @default.
• W3138129969 cites W2028399966 @default.
• W3138129969 cites W2051526952 @default.
• W3138129969 cites W2061681507 @default.
• W3138129969 cites W2061719199 @default.
• W3138129969 cites W2089242029 @default.
• W3138129969 cites W2099397840 @default.
• W3138129969 cites W2108598243 @default.
• W3138129969 cites W2111790388 @default.
• W3138129969 cites W2111935653 @default.
• W3138129969 cites W2125621954 @default.
• W3138129969 cites W2169015768 @default.
• W3138129969 cites W2189774688 @default.
• W3138129969 cites W2194775991 @default.
• W3138129969 cites W2276892413 @default.
• W3138129969 cites W2395500066 @default.
• W3138129969 cites W2460144244 @default.
• W3138129969 cites W2463256602 @default.
• W3138129969 cites W2527749992 @default.
• W3138129969 cites W2557283755 @default.
• W3138129969 cites W2592929672 @default.
• W3138129969 cites W2593744649 @default.
• W3138129969 cites W2605859493 @default.
• W3138129969 cites W2625457103 @default.
• W3138129969 cites W2743651283 @default.
• W3138129969 cites W2797102036 @default.
• W3138129969 cites W2935703330 @default.
• W3138129969 cites W2943283198 @default.
• W3138129969 cites W2946035471 @default.
• W3138129969 cites W2946901414 @default.
• W3138129969 cites W2947607756 @default.
• W3138129969 cites W2948635472 @default.
• W3138129969 cites W2949937757 @default.
• W3138129969 cites W2951189123 @default.
• W3138129969 cites W2955350166 @default.
• W3138129969 cites W2956434358 @default.
• W3138129969 cites W2957180077 @default.
• W3138129969 cites W2961798429 @default.
• W3138129969 cites W2962851801 @default.
• W3138129969 cites W2963363373 @default.
• W3138129969 cites W2963674932 @default.
• W3138129969 cites W2963813662 @default.
• W3138129969 cites W2963828549 @default.
• W3138129969 cites W2964217527 @default.
• W3138129969 cites W2964299589 @default.
• W3138129969 cites W3035180000 @default.
• W3138129969 cites W3143219376 @default.
• W3138129969 hasPublicationYear "2021" @default.
• W3138129969 type Work @default.
• W3138129969 sameAs 3138129969 @default.
• W3138129969 citedByCount "0" @default.
• W3138129969 crossrefType "posted-content" @default.
• W3138129969 hasAuthorship W3138129969A5007627998 @default.
• W3138129969 hasAuthorship W3138129969A5064119706 @default.
• W3138129969 hasAuthorship W3138129969A5069159448 @default.
• W3138129969 hasConcept C111919701 @default.
• W3138129969 hasConcept C11413529 @default.
• W3138129969 hasConcept C115961682 @default.
• W3138129969 hasConcept C119857082 @default.
• W3138129969 hasConcept C124066611 @default.
• W3138129969 hasConcept C134306372 @default.
• W3138129969 hasConcept C153180895 @default.
• W3138129969 hasConcept C154945302 @default.
• W3138129969 hasConcept C162324750 @default.
• W3138129969 hasConcept C177148314 @default.
• W3138129969 hasConcept C2777303404 @default.
• W3138129969 hasConcept C33923547 @default.
• W3138129969 hasConcept C41008148 @default.
• W3138129969 hasConcept C50522688 @default.
• W3138129969 hasConcept C50644808 @default.
• W3138129969 hasConcept C98045186 @default.
• W3138129969 hasConceptScore W3138129969C111919701 @default.
• W3138129969 hasConceptScore W3138129969C11413529 @default.
• W3138129969 hasConceptScore W3138129969C115961682 @default.
• W3138129969 hasConceptScore W3138129969C119857082 @default.
• W3138129969 hasConceptScore W3138129969C124066611 @default.
• W3138129969 hasConceptScore W3138129969C134306372 @default.
• W3138129969 hasConceptScore W3138129969C153180895 @default.
• W3138129969 hasConceptScore W3138129969C154945302 @default.
• W3138129969 hasConceptScore W3138129969C162324750 @default.
• W3138129969 hasConceptScore W3138129969C177148314 @default.
• W3138129969 hasConceptScore W3138129969C2777303404 @default.
• W3138129969 hasConceptScore W3138129969C33923547 @default.
• W3138129969 hasConceptScore W3138129969C41008148 @default.
• W3138129969 hasConceptScore W3138129969C50522688 @default.
• W3138129969 hasConceptScore W3138129969C50644808 @default.

• next