FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036761806> ?p ?o ?g. }

• W3036761806 endingPage "467" @default.
• W3036761806 startingPage "455" @default.
• W3036761806 abstract "Deep learning technologies have been rapidly developing recently. They have shown excellent performances in many fields. However, deep learning networks have weak adaptability to small sample sizes.Usually, deep learning networks require tens of thousands of samples to avoid overfitting. In contrast, the kernel method can deal with small sample sizes. In this paper, we use only dozens of samples to train a successful classifier. Deep multiple kernel learning (DMKL) has emerged in recent years. It combines the ideas of deep learning and multiple kernel learning. Unfortunately, the DMKL network with a fixed structure cannot adapt to data of different dimensions and sizes. Therefore, in this paper, we propose a novel depth-width-scaling multiple kernel learning (DWS-MKL) algorithm. It has the ability to adjust the architecture according to the input data. We optimize the estimation of leave-one-out error by using the span bound instead of the dual objective function. Finally, we choose a large number of data sets from the UCI benchmark data sets for classification tasks. We also evaluate DWS-MKL on the MNIST data set. The experimental results show that different frameworks have different performances on the same dataset. Our DWS-MKL algorithm obtains better classification results than the state-of-the-art kernel learning algorithms, as determined by a thorough comparison. The encouraging results demonstrate that our method has the potential to improve generalization performance of the model." @default.
• W3036761806 created "2020-06-25" @default.
• W3036761806 creator A5045848793 @default.
• W3036761806 creator A5050960882 @default.
• W3036761806 creator A5070555846 @default.
• W3036761806 date "2020-10-01" @default.
• W3036761806 modified "2023-10-16" @default.
• W3036761806 title "DWS-MKL: Depth-width-scaling multiple kernel learning for data classification" @default.
• W3036761806 cites W1560724230 @default.
• W3036761806 cites W1563088657 @default.
• W3036761806 cites W1945125930 @default.
• W3036761806 cites W1967170228 @default.
• W3036761806 cites W2046862341 @default.
• W3036761806 cites W2048041841 @default.
• W3036761806 cites W2060166505 @default.
• W3036761806 cites W2100031962 @default.
• W3036761806 cites W2115390216 @default.
• W3036761806 cites W2133396101 @default.
• W3036761806 cites W2149298154 @default.
• W3036761806 cites W2158001550 @default.
• W3036761806 cites W2161592627 @default.
• W3036761806 cites W2505720795 @default.
• W3036761806 cites W2551683770 @default.
• W3036761806 cites W2561964848 @default.
• W3036761806 cites W2622869899 @default.
• W3036761806 cites W2790182932 @default.
• W3036761806 cites W2893830906 @default.
• W3036761806 cites W2904176920 @default.
• W3036761806 cites W2913783817 @default.
• W3036761806 cites W2939459869 @default.
• W3036761806 cites W2964169082 @default.
• W3036761806 cites W2965052154 @default.
• W3036761806 cites W3101749733 @default.
• W3036761806 cites W4239510810 @default.
• W3036761806 doi "https://doi.org/10.1016/j.neucom.2020.06.039" @default.
• W3036761806 hasPublicationYear "2020" @default.
• W3036761806 type Work @default.
• W3036761806 sameAs 3036761806 @default.
• W3036761806 citedByCount "7" @default.
• W3036761806 countsByYear W30367618062021 @default.
• W3036761806 countsByYear W30367618062022 @default.
• W3036761806 countsByYear W30367618062023 @default.
• W3036761806 crossrefType "journal-article" @default.
• W3036761806 hasAuthorship W3036761806A5045848793 @default.
• W3036761806 hasAuthorship W3036761806A5050960882 @default.
• W3036761806 hasAuthorship W3036761806A5070555846 @default.
• W3036761806 hasConcept C108583219 @default.
• W3036761806 hasConcept C114614502 @default.
• W3036761806 hasConcept C119857082 @default.
• W3036761806 hasConcept C122280245 @default.
• W3036761806 hasConcept C12267149 @default.
• W3036761806 hasConcept C13280743 @default.
• W3036761806 hasConcept C153180895 @default.
• W3036761806 hasConcept C154945302 @default.
• W3036761806 hasConcept C177606310 @default.
• W3036761806 hasConcept C185798385 @default.
• W3036761806 hasConcept C18903297 @default.
• W3036761806 hasConcept C190502265 @default.
• W3036761806 hasConcept C205649164 @default.
• W3036761806 hasConcept C22019652 @default.
• W3036761806 hasConcept C2776879701 @default.
• W3036761806 hasConcept C33923547 @default.
• W3036761806 hasConcept C41008148 @default.
• W3036761806 hasConcept C50644808 @default.
• W3036761806 hasConcept C74193536 @default.
• W3036761806 hasConcept C86803240 @default.
• W3036761806 hasConcept C95623464 @default.
• W3036761806 hasConceptScore W3036761806C108583219 @default.
• W3036761806 hasConceptScore W3036761806C114614502 @default.
• W3036761806 hasConceptScore W3036761806C119857082 @default.
• W3036761806 hasConceptScore W3036761806C122280245 @default.
• W3036761806 hasConceptScore W3036761806C12267149 @default.
• W3036761806 hasConceptScore W3036761806C13280743 @default.
• W3036761806 hasConceptScore W3036761806C153180895 @default.
• W3036761806 hasConceptScore W3036761806C154945302 @default.
• W3036761806 hasConceptScore W3036761806C177606310 @default.
• W3036761806 hasConceptScore W3036761806C185798385 @default.
• W3036761806 hasConceptScore W3036761806C18903297 @default.
• W3036761806 hasConceptScore W3036761806C190502265 @default.
• W3036761806 hasConceptScore W3036761806C205649164 @default.
• W3036761806 hasConceptScore W3036761806C22019652 @default.
• W3036761806 hasConceptScore W3036761806C2776879701 @default.
• W3036761806 hasConceptScore W3036761806C33923547 @default.
• W3036761806 hasConceptScore W3036761806C41008148 @default.
• W3036761806 hasConceptScore W3036761806C50644808 @default.
• W3036761806 hasConceptScore W3036761806C74193536 @default.
• W3036761806 hasConceptScore W3036761806C86803240 @default.
• W3036761806 hasConceptScore W3036761806C95623464 @default.
• W3036761806 hasLocation W30367618061 @default.
• W3036761806 hasOpenAccess W3036761806 @default.
• W3036761806 hasPrimaryLocation W30367618061 @default.
• W3036761806 hasRelatedWork W2055608878 @default.
• W3036761806 hasRelatedWork W2133046540 @default.
• W3036761806 hasRelatedWork W2144299089 @default.
• W3036761806 hasRelatedWork W2570832236 @default.
• W3036761806 hasRelatedWork W2725311638 @default.
• W3036761806 hasRelatedWork W2783388698 @default.
• W3036761806 hasRelatedWork W2987302549 @default.

• next