Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133672348> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3133672348 endingPage "2171" @default.
- W3133672348 startingPage "2171" @default.
- W3133672348 abstract "Incremental learning is a methodology that continuously uses the sequential input data to extend the existing network’s knowledge. The layer sharing algorithm is one of the representative methods which leverages general knowledge by sharing some initial layers of the existing network. To determine the performance of the incremental network, it is critical to estimate how much the initial convolutional layers in the existing network can be shared as the fixed feature extractors. However, the existing algorithm selects the sharing configuration through improper optimization strategy but a brute force manner such as searching for all possible sharing layers case. This is a non-convex and non-differential problem. Accordingly, this can not be solved using powerful optimization techniques such as the gradient descent algorithm or other convex optimization problem, and it leads to high computational complexity. To solve this problem, we firstly define this as a discrete combinatorial optimization problem, and propose a novel efficient incremental learning algorithm-based Bayesian optimization, which guarantees the global convergence in a non-convex and non-differential optimization. Additionally, our proposed algorithm can adaptively find the optimal number of sharing layers via adjusting the threshold accuracy parameter in the proposed loss function. With the proposed method, the global optimal sharing layer can be found in only six or eight iterations without searching for all possible layer cases. Hence, the proposed method can find the global optimal sharing layers by utilizing Bayesian optimization, which achieves both high combined accuracy and low computational complexity." @default.
- W3133672348 created "2021-03-15" @default.
- W3133672348 creator A5047204534 @default.
- W3133672348 creator A5059701191 @default.
- W3133672348 creator A5085747593 @default.
- W3133672348 date "2021-03-01" @default.
- W3133672348 modified "2023-10-08" @default.
- W3133672348 title "Bayesian Optimization Based Efficient Layer Sharing for Incremental Learning" @default.
- W3133672348 cites W2004906124 @default.
- W3133672348 cites W2060277733 @default.
- W3133672348 cites W2061144551 @default.
- W3133672348 cites W2113759470 @default.
- W3133672348 cites W2156406284 @default.
- W3133672348 cites W2165698076 @default.
- W3133672348 cites W2473930607 @default.
- W3133672348 cites W2773246426 @default.
- W3133672348 cites W2799985340 @default.
- W3133672348 cites W3001774049 @default.
- W3133672348 cites W3041133507 @default.
- W3133672348 doi "https://doi.org/10.3390/app11052171" @default.
- W3133672348 hasPublicationYear "2021" @default.
- W3133672348 type Work @default.
- W3133672348 sameAs 3133672348 @default.
- W3133672348 citedByCount "2" @default.
- W3133672348 countsByYear W31336723482022 @default.
- W3133672348 crossrefType "journal-article" @default.
- W3133672348 hasAuthorship W3133672348A5047204534 @default.
- W3133672348 hasAuthorship W3133672348A5059701191 @default.
- W3133672348 hasAuthorship W3133672348A5085747593 @default.
- W3133672348 hasBestOaLocation W31336723481 @default.
- W3133672348 hasConcept C112680207 @default.
- W3133672348 hasConcept C11413529 @default.
- W3133672348 hasConcept C126255220 @default.
- W3133672348 hasConcept C137836250 @default.
- W3133672348 hasConcept C154945302 @default.
- W3133672348 hasConcept C157972887 @default.
- W3133672348 hasConcept C162324750 @default.
- W3133672348 hasConcept C2524010 @default.
- W3133672348 hasConcept C2777303404 @default.
- W3133672348 hasConcept C2778049539 @default.
- W3133672348 hasConcept C33724603 @default.
- W3133672348 hasConcept C33923547 @default.
- W3133672348 hasConcept C41008148 @default.
- W3133672348 hasConcept C50522688 @default.
- W3133672348 hasConceptScore W3133672348C112680207 @default.
- W3133672348 hasConceptScore W3133672348C11413529 @default.
- W3133672348 hasConceptScore W3133672348C126255220 @default.
- W3133672348 hasConceptScore W3133672348C137836250 @default.
- W3133672348 hasConceptScore W3133672348C154945302 @default.
- W3133672348 hasConceptScore W3133672348C157972887 @default.
- W3133672348 hasConceptScore W3133672348C162324750 @default.
- W3133672348 hasConceptScore W3133672348C2524010 @default.
- W3133672348 hasConceptScore W3133672348C2777303404 @default.
- W3133672348 hasConceptScore W3133672348C2778049539 @default.
- W3133672348 hasConceptScore W3133672348C33724603 @default.
- W3133672348 hasConceptScore W3133672348C33923547 @default.
- W3133672348 hasConceptScore W3133672348C41008148 @default.
- W3133672348 hasConceptScore W3133672348C50522688 @default.
- W3133672348 hasIssue "5" @default.
- W3133672348 hasLocation W31336723481 @default.
- W3133672348 hasLocation W31336723482 @default.
- W3133672348 hasOpenAccess W3133672348 @default.
- W3133672348 hasPrimaryLocation W31336723481 @default.
- W3133672348 hasRelatedWork W2765202572 @default.
- W3133672348 hasRelatedWork W2811008754 @default.
- W3133672348 hasRelatedWork W2953109382 @default.
- W3133672348 hasRelatedWork W3188540459 @default.
- W3133672348 hasRelatedWork W4287753921 @default.
- W3133672348 hasRelatedWork W4294892986 @default.
- W3133672348 hasRelatedWork W4306295037 @default.
- W3133672348 hasRelatedWork W4312405383 @default.
- W3133672348 hasRelatedWork W4381283837 @default.
- W3133672348 hasRelatedWork W990771678 @default.
- W3133672348 hasVolume "11" @default.
- W3133672348 isParatext "false" @default.
- W3133672348 isRetracted "false" @default.
- W3133672348 magId "3133672348" @default.
- W3133672348 workType "article" @default.