Matches in SemOpenAlex for { <https://semopenalex.org/work/W3162132941> ?p ?o ?g. }
- W3162132941 abstract "Due to the dominant position of deep learning (mostly deep neural networks) in various artificial intelligence applications, recently, ensemble learning based on deep neural networks (ensemble deep learning) has shown significant performances in improving the generalization of learning system. However, since modern deep neural networks usually have millions to billions of parameters, the time and space overheads for training multiple base deep learners and testing with the ensemble deep learner are far greater than that of traditional ensemble learning. Though several algorithms of fast ensemble deep learning have been proposed to promote the deployment of ensemble deep learning in some applications, further advances still need to be made for many applications in specific fields, where the developing time and computing resources are usually restricted or the data to be processed is of large dimensionality. An urgent problem needs to be solved is how to take the significant advantages of ensemble deep learning while reduce the required expenses so that many more applications in specific fields can benefit from it. For the alleviation of this problem, it is essential to know about how ensemble learning has developed under the era of deep learning. Thus, in this article, we present fundamental discussions focusing on data analyses of published works, methodologies, recent advances and unattainability of traditional ensemble learning and ensemble deep learning. We hope this article will be helpful to realize the intrinsic problems and technical challenges faced by future developments of ensemble learning under the era of deep learning." @default.
- W3162132941 created "2021-05-24" @default.
- W3162132941 creator A5012247372 @default.
- W3162132941 creator A5074504268 @default.
- W3162132941 creator A5080298585 @default.
- W3162132941 date "2021-01-20" @default.
- W3162132941 modified "2023-10-17" @default.
- W3162132941 title "A Survey on Ensemble Learning under the Era of Deep Learning" @default.
- W3162132941 cites W1040574815 @default.
- W3162132941 cites W1496929357 @default.
- W3162132941 cites W1498436455 @default.
- W3162132941 cites W1499586235 @default.
- W3162132941 cites W1534477342 @default.
- W3162132941 cites W1582036668 @default.
- W3162132941 cites W1595159159 @default.
- W3162132941 cites W1600744878 @default.
- W3162132941 cites W1603903339 @default.
- W3162132941 cites W1614298861 @default.
- W3162132941 cites W1662894842 @default.
- W3162132941 cites W1676820704 @default.
- W3162132941 cites W1678356000 @default.
- W3162132941 cites W1854214752 @default.
- W3162132941 cites W1901129140 @default.
- W3162132941 cites W1922017469 @default.
- W3162132941 cites W1964675863 @default.
- W3162132941 cites W1965895201 @default.
- W3162132941 cites W1967217515 @default.
- W3162132941 cites W1972860770 @default.
- W3162132941 cites W1977020076 @default.
- W3162132941 cites W1977177161 @default.
- W3162132941 cites W1979759959 @default.
- W3162132941 cites W1982267716 @default.
- W3162132941 cites W1982761740 @default.
- W3162132941 cites W1983434966 @default.
- W3162132941 cites W1985258161 @default.
- W3162132941 cites W1988790447 @default.
- W3162132941 cites W1993506032 @default.
- W3162132941 cites W2000292092 @default.
- W3162132941 cites W2003303386 @default.
- W3162132941 cites W2007221293 @default.
- W3162132941 cites W2016794826 @default.
- W3162132941 cites W2022747340 @default.
- W3162132941 cites W2025444507 @default.
- W3162132941 cites W2025768430 @default.
- W3162132941 cites W2033018833 @default.
- W3162132941 cites W2042053856 @default.
- W3162132941 cites W2046842005 @default.
- W3162132941 cites W2061082730 @default.
- W3162132941 cites W2061119986 @default.
- W3162132941 cites W2061576204 @default.
- W3162132941 cites W2062024414 @default.
- W3162132941 cites W2064675550 @default.
- W3162132941 cites W2065642067 @default.
- W3162132941 cites W2066334462 @default.
- W3162132941 cites W2086576008 @default.
- W3162132941 cites W2089367555 @default.
- W3162132941 cites W2089468765 @default.
- W3162132941 cites W2093717447 @default.
- W3162132941 cites W2098028543 @default.
- W3162132941 cites W2100128988 @default.
- W3162132941 cites W2100495367 @default.
- W3162132941 cites W2103346566 @default.
- W3162132941 cites W2108949035 @default.
- W3162132941 cites W2110802877 @default.
- W3162132941 cites W2110819057 @default.
- W3162132941 cites W2112076978 @default.
- W3162132941 cites W2112796928 @default.
- W3162132941 cites W2113242816 @default.
- W3162132941 cites W2114024619 @default.
- W3162132941 cites W2120390927 @default.
- W3162132941 cites W2121971770 @default.
- W3162132941 cites W2125055259 @default.
- W3162132941 cites W2125056386 @default.
- W3162132941 cites W2129531883 @default.
- W3162132941 cites W2131744502 @default.
- W3162132941 cites W2132984323 @default.
- W3162132941 cites W2135293965 @default.
- W3162132941 cites W2136922672 @default.
- W3162132941 cites W2139237500 @default.
- W3162132941 cites W2142827986 @default.
- W3162132941 cites W2143720865 @default.
- W3162132941 cites W2144463230 @default.
- W3162132941 cites W2145094598 @default.
- W3162132941 cites W2146927999 @default.
- W3162132941 cites W2149706766 @default.
- W3162132941 cites W2150757437 @default.
- W3162132941 cites W2152239989 @default.
- W3162132941 cites W2152705149 @default.
- W3162132941 cites W2152761983 @default.
- W3162132941 cites W2153635508 @default.
- W3162132941 cites W2155893237 @default.
- W3162132941 cites W2158863190 @default.
- W3162132941 cites W2161940528 @default.
- W3162132941 cites W2162384303 @default.
- W3162132941 cites W2162392441 @default.
- W3162132941 cites W2170123469 @default.
- W3162132941 cites W2183341477 @default.
- W3162132941 cites W2194775991 @default.
- W3162132941 cites W2205505631 @default.
- W3162132941 cites W2219903032 @default.