Matches in SemOpenAlex for { <https://semopenalex.org/work/W2003147851> ?p ?o ?g. }
- W2003147851 endingPage "40" @default.
- W2003147851 startingPage "20" @default.
- W2003147851 abstract "The backpropagation (BP) algorithm is the most commonly utilized training strategy for a feed-forward artificial neural network (FFANN). The BP algorithm, however, always leads to the problems of low convergence rate, high energy and poor generalization capability of FFANN. In this paper, motivated by the sparsity property of human neuron’ responses, we introduce a new sparse-response BP (SRBP) to improve the capacity of a FFANN by enforcing sparsity to its hidden units through imposing a supplemental L1 term on them. The FFANN model learned from our algorithm is closely related to the real human and thus its mechanism fully complies with the human nervous system, i.e., sparse representation and architectural depth. Experiments on several datasets demonstrate that SRBP yields good performances on convergence rate, energy saving and generalization capability." @default.
- W2003147851 created "2016-06-24" @default.
- W2003147851 creator A5014312349 @default.
- W2003147851 creator A5024865534 @default.
- W2003147851 creator A5024880206 @default.
- W2003147851 creator A5087572706 @default.
- W2003147851 creator A5091017287 @default.
- W2003147851 date "2015-04-01" @default.
- W2003147851 modified "2023-10-15" @default.
- W2003147851 title "Enhancing performance of the backpropagation algorithm via sparse response regularization" @default.
- W2003147851 cites W1620759536 @default.
- W2003147851 cites W1788984484 @default.
- W2003147851 cites W1971014294 @default.
- W2003147851 cites W1977345805 @default.
- W2003147851 cites W1978660892 @default.
- W2003147851 cites W1981025032 @default.
- W2003147851 cites W1987238397 @default.
- W2003147851 cites W1995636681 @default.
- W2003147851 cites W1997587690 @default.
- W2003147851 cites W2001312363 @default.
- W2003147851 cites W2005971284 @default.
- W2003147851 cites W2011873184 @default.
- W2003147851 cites W2013239224 @default.
- W2003147851 cites W2026765215 @default.
- W2003147851 cites W2028069051 @default.
- W2003147851 cites W2067706439 @default.
- W2003147851 cites W2074376560 @default.
- W2003147851 cites W2091632079 @default.
- W2003147851 cites W2092859712 @default.
- W2003147851 cites W2096828462 @default.
- W2003147851 cites W2099791377 @default.
- W2003147851 cites W2105050785 @default.
- W2003147851 cites W2107647130 @default.
- W2003147851 cites W2110179049 @default.
- W2003147851 cites W2122297221 @default.
- W2003147851 cites W2129131372 @default.
- W2003147851 cites W2133640977 @default.
- W2003147851 cites W2142105298 @default.
- W2003147851 cites W2142544077 @default.
- W2003147851 cites W2145889472 @default.
- W2003147851 cites W2150579376 @default.
- W2003147851 cites W2156297475 @default.
- W2003147851 cites W2167736532 @default.
- W2003147851 cites W2172174689 @default.
- W2003147851 cites W2951692858 @default.
- W2003147851 cites W4231109964 @default.
- W2003147851 cites W4239510810 @default.
- W2003147851 cites W4250955649 @default.
- W2003147851 doi "https://doi.org/10.1016/j.neucom.2014.11.055" @default.
- W2003147851 hasPublicationYear "2015" @default.
- W2003147851 type Work @default.
- W2003147851 sameAs 2003147851 @default.
- W2003147851 citedByCount "14" @default.
- W2003147851 countsByYear W20031478512015 @default.
- W2003147851 countsByYear W20031478512016 @default.
- W2003147851 countsByYear W20031478512017 @default.
- W2003147851 countsByYear W20031478512018 @default.
- W2003147851 countsByYear W20031478512019 @default.
- W2003147851 countsByYear W20031478512020 @default.
- W2003147851 countsByYear W20031478512021 @default.
- W2003147851 crossrefType "journal-article" @default.
- W2003147851 hasAuthorship W2003147851A5014312349 @default.
- W2003147851 hasAuthorship W2003147851A5024865534 @default.
- W2003147851 hasAuthorship W2003147851A5024880206 @default.
- W2003147851 hasAuthorship W2003147851A5087572706 @default.
- W2003147851 hasAuthorship W2003147851A5091017287 @default.
- W2003147851 hasConcept C105795698 @default.
- W2003147851 hasConcept C111472728 @default.
- W2003147851 hasConcept C11413529 @default.
- W2003147851 hasConcept C134306372 @default.
- W2003147851 hasConcept C138885662 @default.
- W2003147851 hasConcept C154945302 @default.
- W2003147851 hasConcept C155032097 @default.
- W2003147851 hasConcept C162324750 @default.
- W2003147851 hasConcept C177148314 @default.
- W2003147851 hasConcept C17744445 @default.
- W2003147851 hasConcept C186370098 @default.
- W2003147851 hasConcept C189950617 @default.
- W2003147851 hasConcept C199539241 @default.
- W2003147851 hasConcept C26517878 @default.
- W2003147851 hasConcept C2776135515 @default.
- W2003147851 hasConcept C2776359362 @default.
- W2003147851 hasConcept C2777303404 @default.
- W2003147851 hasConcept C33923547 @default.
- W2003147851 hasConcept C38652104 @default.
- W2003147851 hasConcept C41008148 @default.
- W2003147851 hasConcept C50522688 @default.
- W2003147851 hasConcept C50644808 @default.
- W2003147851 hasConcept C57869625 @default.
- W2003147851 hasConcept C94625758 @default.
- W2003147851 hasConceptScore W2003147851C105795698 @default.
- W2003147851 hasConceptScore W2003147851C111472728 @default.
- W2003147851 hasConceptScore W2003147851C11413529 @default.
- W2003147851 hasConceptScore W2003147851C134306372 @default.
- W2003147851 hasConceptScore W2003147851C138885662 @default.
- W2003147851 hasConceptScore W2003147851C154945302 @default.
- W2003147851 hasConceptScore W2003147851C155032097 @default.
- W2003147851 hasConceptScore W2003147851C162324750 @default.