FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2593968685> ?p ?o ?g. }

• W2593968685 abstract "Graphical abstractDisplay Omitted HighlightsWe consider the optimal solution for the linear guided autoencoder (LGAE) we call that addresses both unsupervised and supervised learning simultaneously.In order to linearize the encoding function in the LGAE, we provide a first-order approximation to the optimal solution and to determine the necessary condition for linear solution, which aims knowledge acquisition from the LGAE.We present the connection between the LGAE and partial least squares from the perspective of information theory for the denoising autoencoders.We validate our method on benchmark datasets, and then apply the LGAE to a dataset of methane storage materials in order to predict the methane uptake. In materials science, good representations of materials are important for use with prediction models in order to ensure accurate prediction of the properties of the output. In this paper, in order to address this issue, we use a learning system, linear guided autoencoder (LGAE) we call, which consists of an autoencoder and a linear predictor. For the autoencoder, we adopt a variant of the denoising autoencoder. In the LGAE, the learning addresses the unsupervised and supervised tasks simultaneously. Thus, the LGAE can be regarded as a form of nonlinear partial least squares (PLS) regression. Previous studies have not found the optimal solution for the encoder for an objective that contains both tasks. Our main contributions are a first-order approximation of the optimal solution and determination of the condition for linear solution that applies to the LGAE after training, in order to acquire knowledge from the nonlinear model (i.e., the LGAE). The main drawback of nonlinear PLS regression is that it is difficult to interpret the latent representation. Therefore, we propose a technical method for interpreting the latent representation. Experiments on benchmark datasets are conducted in order to compare the LGAE with kernel PLS regression, which is a powerful nonlinear PLS regression method. We also applied the LGAE to a dataset of methane storage materials in order to interpret the methane uptake based on the input variables and obtained reasonable results." @default.
• W2593968685 created "2017-03-16" @default.
• W2593968685 creator A5054306405 @default.
• W2593968685 date "2017-06-01" @default.
• W2593968685 modified "2023-09-23" @default.
• W2593968685 title "Linear guided autoencoder: Representation learning with linearity" @default.
• W2593968685 cites W1545687120 @default.
• W2593968685 cites W1545920196 @default.
• W2593968685 cites W1665214252 @default.
• W2593968685 cites W1796128977 @default.
• W2593968685 cites W1937777952 @default.
• W2593968685 cites W1967734070 @default.
• W2593968685 cites W1977053243 @default.
• W2593968685 cites W1999798000 @default.
• W2593968685 cites W2013035813 @default.
• W2593968685 cites W2023745373 @default.
• W2593968685 cites W2025768430 @default.
• W2593968685 cites W2047909810 @default.
• W2593968685 cites W2051801258 @default.
• W2593968685 cites W2073503722 @default.
• W2593968685 cites W2095705004 @default.
• W2593968685 cites W2097998348 @default.
• W2593968685 cites W2100341991 @default.
• W2593968685 cites W2100716186 @default.
• W2593968685 cites W2102409316 @default.
• W2593968685 cites W2110798204 @default.
• W2593968685 cites W2111406701 @default.
• W2593968685 cites W2133294540 @default.
• W2593968685 cites W2135306627 @default.
• W2593968685 cites W2136922672 @default.
• W2593968685 cites W2137211388 @default.
• W2593968685 cites W2137225583 @default.
• W2593968685 cites W2137983211 @default.
• W2593968685 cites W2138857742 @default.
• W2593968685 cites W2139269942 @default.
• W2593968685 cites W2141879504 @default.
• W2593968685 cites W2145094598 @default.
• W2593968685 cites W2160815625 @default.
• W2593968685 cites W2161388792 @default.
• W2593968685 cites W2162262658 @default.
• W2593968685 cites W2163922914 @default.
• W2593968685 cites W2164370980 @default.
• W2593968685 cites W2165901038 @default.
• W2593968685 cites W2170917242 @default.
• W2593968685 cites W2187483593 @default.
• W2593968685 cites W2257979135 @default.
• W2593968685 cites W2280377497 @default.
• W2593968685 cites W2281948289 @default.
• W2593968685 cites W2295582178 @default.
• W2593968685 cites W2316126360 @default.
• W2593968685 cites W2344593201 @default.
• W2593968685 cites W2522012644 @default.
• W2593968685 cites W2536690816 @default.
• W2593968685 cites W2557283755 @default.
• W2593968685 cites W2584401907 @default.
• W2593968685 cites W2606321545 @default.
• W2593968685 cites W2613634265 @default.
• W2593968685 cites W2614634292 @default.
• W2593968685 cites W2618530766 @default.
• W2593968685 cites W2919115771 @default.
• W2593968685 cites W2963026564 @default.
• W2593968685 cites W3146803896 @default.
• W2593968685 cites W3147600416 @default.
• W2593968685 cites W35527955 @default.
• W2593968685 cites W36040755 @default.
• W2593968685 cites W2490363635 @default.
• W2593968685 doi "https://doi.org/10.1016/j.asoc.2017.02.019" @default.
• W2593968685 hasPublicationYear "2017" @default.
• W2593968685 type Work @default.
• W2593968685 sameAs 2593968685 @default.
• W2593968685 citedByCount "7" @default.
• W2593968685 countsByYear W25939686852017 @default.
• W2593968685 countsByYear W25939686852019 @default.
• W2593968685 countsByYear W25939686852020 @default.
• W2593968685 crossrefType "journal-article" @default.
• W2593968685 hasAuthorship W2593968685A5054306405 @default.
• W2593968685 hasConcept C101738243 @default.
• W2593968685 hasConcept C108583219 @default.
• W2593968685 hasConcept C111919701 @default.
• W2593968685 hasConcept C118505674 @default.
• W2593968685 hasConcept C119857082 @default.
• W2593968685 hasConcept C121332964 @default.
• W2593968685 hasConcept C125411270 @default.
• W2593968685 hasConcept C126255220 @default.
• W2593968685 hasConcept C13280743 @default.
• W2593968685 hasConcept C153180895 @default.
• W2593968685 hasConcept C154945302 @default.
• W2593968685 hasConcept C158622935 @default.
• W2593968685 hasConcept C185798385 @default.
• W2593968685 hasConcept C205649164 @default.
• W2593968685 hasConcept C33923547 @default.
• W2593968685 hasConcept C41008148 @default.
• W2593968685 hasConcept C62520636 @default.
• W2593968685 hasConcept C8038995 @default.
• W2593968685 hasConceptScore W2593968685C101738243 @default.
• W2593968685 hasConceptScore W2593968685C108583219 @default.
• W2593968685 hasConceptScore W2593968685C111919701 @default.
• W2593968685 hasConceptScore W2593968685C118505674 @default.
• W2593968685 hasConceptScore W2593968685C119857082 @default.
• W2593968685 hasConceptScore W2593968685C121332964 @default.

• next