Matches in SemOpenAlex for { <https://semopenalex.org/work/W2055505399> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W2055505399 abstract "This paper proposes a global learning of neural networks by hybrid optimization algorithm. The hybrid algorithm combines a stochastic approximation with a gradient descent. The stochastic approximation is first applied for estimating an approximation point inclined toward a global escaping from a local minimum, and then the backpropagation(BP) algorithm is applied for high-speed convergence as gradient descent. The proposed method has been applied to 8-bit parity check and 6-bit symmetry check problems, respectively. The experimental results show that the proposed method has superior convergence performances to the conventional method that is BP algorithm with randomized initial weights setting." @default.
- W2055505399 created "2016-06-24" @default.
- W2055505399 creator A5021748549 @default.
- W2055505399 creator A5066387980 @default.
- W2055505399 date "2007-01-01" @default.
- W2055505399 modified "2023-10-14" @default.
- W2055505399 title "Global Learning of Neural Networks by Using Hybrid Optimization Algorithm" @default.
- W2055505399 cites W1537579380 @default.
- W2055505399 cites W1562895369 @default.
- W2055505399 cites W1603765807 @default.
- W2055505399 cites W2003243598 @default.
- W2055505399 cites W2027867903 @default.
- W2055505399 cites W2044286864 @default.
- W2055505399 cites W2057814197 @default.
- W2055505399 cites W2084260228 @default.
- W2055505399 doi "https://doi.org/10.2991/iske.2007.201" @default.
- W2055505399 hasPublicationYear "2007" @default.
- W2055505399 type Work @default.
- W2055505399 sameAs 2055505399 @default.
- W2055505399 citedByCount "0" @default.
- W2055505399 crossrefType "proceedings-article" @default.
- W2055505399 hasAuthorship W2055505399A5021748549 @default.
- W2055505399 hasAuthorship W2055505399A5066387980 @default.
- W2055505399 hasBestOaLocation W20555053991 @default.
- W2055505399 hasConcept C11413529 @default.
- W2055505399 hasConcept C126255220 @default.
- W2055505399 hasConcept C154945302 @default.
- W2055505399 hasConcept C2987595161 @default.
- W2055505399 hasConcept C33923547 @default.
- W2055505399 hasConcept C41008148 @default.
- W2055505399 hasConcept C50644808 @default.
- W2055505399 hasConceptScore W2055505399C11413529 @default.
- W2055505399 hasConceptScore W2055505399C126255220 @default.
- W2055505399 hasConceptScore W2055505399C154945302 @default.
- W2055505399 hasConceptScore W2055505399C2987595161 @default.
- W2055505399 hasConceptScore W2055505399C33923547 @default.
- W2055505399 hasConceptScore W2055505399C41008148 @default.
- W2055505399 hasConceptScore W2055505399C50644808 @default.
- W2055505399 hasLocation W20555053991 @default.
- W2055505399 hasLocation W20555053992 @default.
- W2055505399 hasOpenAccess W2055505399 @default.
- W2055505399 hasPrimaryLocation W20555053991 @default.
- W2055505399 hasRelatedWork W2351491280 @default.
- W2055505399 hasRelatedWork W2356957943 @default.
- W2055505399 hasRelatedWork W2359549665 @default.
- W2055505399 hasRelatedWork W2371447506 @default.
- W2055505399 hasRelatedWork W2380313759 @default.
- W2055505399 hasRelatedWork W2386387936 @default.
- W2055505399 hasRelatedWork W2386767533 @default.
- W2055505399 hasRelatedWork W2392110728 @default.
- W2055505399 hasRelatedWork W303980170 @default.
- W2055505399 hasRelatedWork W1629725936 @default.
- W2055505399 isParatext "false" @default.
- W2055505399 isRetracted "false" @default.
- W2055505399 magId "2055505399" @default.
- W2055505399 workType "article" @default.