Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893196123> ?p ?o ?g. }
- W2893196123 endingPage "68" @default.
- W2893196123 startingPage "44" @default.
- W2893196123 abstract "In recent years, unsupervised feature learning based on a neural network architecture has become a hot new topic for research [1]-[4]. The revival of interest in such deep networks can be attributed to the development of efficient optimization skills, by which the model parameters can be optimally estimated [5]. The milestone work done by Hinton and Salakhutdinov [6] proposes to initialize the weights that allow deep autoencoder networks to learn lowdimensional codes. The encoding trick introduced works much better than principal component analysis (PCA) in terms of dimension reduction." @default.
- W2893196123 created "2018-10-05" @default.
- W2893196123 creator A5034852790 @default.
- W2893196123 creator A5052210425 @default.
- W2893196123 creator A5058394999 @default.
- W2893196123 creator A5082887216 @default.
- W2893196123 date "2018-09-01" @default.
- W2893196123 modified "2023-10-13" @default.
- W2893196123 title "A Review of the Autoencoder and Its Variants: A Comparative Perspective from Target Recognition in Synthetic-Aperture Radar Images" @default.
- W2893196123 cites W1560922506 @default.
- W2893196123 cites W1571809481 @default.
- W2893196123 cites W1920235975 @default.
- W2893196123 cites W1972756357 @default.
- W2893196123 cites W1978379919 @default.
- W2893196123 cites W1989316905 @default.
- W2893196123 cites W1990895816 @default.
- W2893196123 cites W2006603039 @default.
- W2893196123 cites W2018880432 @default.
- W2893196123 cites W2026945162 @default.
- W2893196123 cites W2029316659 @default.
- W2893196123 cites W2035054708 @default.
- W2893196123 cites W2038501427 @default.
- W2893196123 cites W2038591350 @default.
- W2893196123 cites W2044931739 @default.
- W2893196123 cites W2060038468 @default.
- W2893196123 cites W2064630666 @default.
- W2893196123 cites W2070452328 @default.
- W2893196123 cites W2084346099 @default.
- W2893196123 cites W2086866337 @default.
- W2893196123 cites W2100495367 @default.
- W2893196123 cites W2109900939 @default.
- W2893196123 cites W2111525901 @default.
- W2893196123 cites W2124648367 @default.
- W2893196123 cites W2126176832 @default.
- W2893196123 cites W2129812935 @default.
- W2893196123 cites W2130615595 @default.
- W2893196123 cites W2136922672 @default.
- W2893196123 cites W2138287042 @default.
- W2893196123 cites W2140619591 @default.
- W2893196123 cites W2143747537 @default.
- W2893196123 cites W2144354855 @default.
- W2893196123 cites W2147228188 @default.
- W2893196123 cites W2148791593 @default.
- W2893196123 cites W2149918662 @default.
- W2893196123 cites W2163922914 @default.
- W2893196123 cites W2179290474 @default.
- W2893196123 cites W2207374674 @default.
- W2893196123 cites W2301541953 @default.
- W2893196123 cites W2342880667 @default.
- W2893196123 cites W2344340558 @default.
- W2893196123 cites W2345128667 @default.
- W2893196123 cites W2345852998 @default.
- W2893196123 cites W2410591237 @default.
- W2893196123 cites W2417947228 @default.
- W2893196123 cites W2492018752 @default.
- W2893196123 cites W2533228971 @default.
- W2893196123 cites W2549293537 @default.
- W2893196123 cites W2574739416 @default.
- W2893196123 cites W2578577414 @default.
- W2893196123 cites W2588677815 @default.
- W2893196123 cites W2589263706 @default.
- W2893196123 cites W2591702764 @default.
- W2893196123 cites W2592224809 @default.
- W2893196123 cites W2593886839 @default.
- W2893196123 cites W2596473454 @default.
- W2893196123 cites W2597000936 @default.
- W2893196123 cites W2603834682 @default.
- W2893196123 cites W2604973793 @default.
- W2893196123 cites W2610921225 @default.
- W2893196123 cites W2611271568 @default.
- W2893196123 cites W2613063417 @default.
- W2893196123 cites W2615263668 @default.
- W2893196123 cites W2617818785 @default.
- W2893196123 cites W2724081917 @default.
- W2893196123 cites W2737996023 @default.
- W2893196123 cites W2744389347 @default.
- W2893196123 cites W2750575765 @default.
- W2893196123 cites W2754361766 @default.
- W2893196123 cites W2756157229 @default.
- W2893196123 cites W2764108700 @default.
- W2893196123 cites W2765832304 @default.
- W2893196123 cites W2765923665 @default.
- W2893196123 cites W2766299269 @default.
- W2893196123 cites W2767966434 @default.
- W2893196123 cites W2768731046 @default.
- W2893196123 cites W2769692579 @default.
- W2893196123 cites W2770727026 @default.
- W2893196123 cites W2776526448 @default.
- W2893196123 cites W2779530678 @default.
- W2893196123 cites W2781622318 @default.
- W2893196123 cites W2782750212 @default.
- W2893196123 cites W2783074568 @default.
- W2893196123 cites W2789436454 @default.
- W2893196123 cites W2790128178 @default.
- W2893196123 cites W2963166639 @default.
- W2893196123 cites W3041793138 @default.
- W2893196123 doi "https://doi.org/10.1109/mgrs.2018.2853555" @default.
- W2893196123 hasPublicationYear "2018" @default.