Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133902371> ?p ?o ?g. }
- W3133902371 endingPage "44" @default.
- W3133902371 startingPage "18" @default.
- W3133902371 abstract "Deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets. An emerging technique called algorithm unrolling, or unfolding, offers promise in eliminating these issues by providing a concrete and systematic connection between iterative algorithms that are widely used in signal processing and deep neural networks. Unrolling methods were first proposed to develop fast neural network approximations for sparse coding. More recently, this direction has attracted enormous attention, and it is rapidly growing in both theoretic investigations and practical applications. The increasing popularity of unrolled deep networks is due, in part, to their potential in developing efficient, high-performance (yet interpretable) network architectures from reasonably sized training sets." @default.
- W3133902371 created "2021-03-15" @default.
- W3133902371 creator A5005913897 @default.
- W3133902371 creator A5014013504 @default.
- W3133902371 creator A5015969128 @default.
- W3133902371 date "2021-03-01" @default.
- W3133902371 modified "2023-10-18" @default.
- W3133902371 title "Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing" @default.
- W3133902371 cites W1457323852 @default.
- W3133902371 cites W1581808154 @default.
- W3133902371 cites W1677182931 @default.
- W3133902371 cites W1885185971 @default.
- W3133902371 cites W1901129140 @default.
- W3133902371 cites W1902027874 @default.
- W3133902371 cites W1903029394 @default.
- W3133902371 cites W1906770428 @default.
- W3133902371 cites W1919542679 @default.
- W3133902371 cites W1999726054 @default.
- W3133902371 cites W2030161963 @default.
- W3133902371 cites W2039844283 @default.
- W3133902371 cites W2077646121 @default.
- W3133902371 cites W2082029531 @default.
- W3133902371 cites W2100556411 @default.
- W3133902371 cites W2101926813 @default.
- W3133902371 cites W2103496339 @default.
- W3133902371 cites W2108598243 @default.
- W3133902371 cites W2116360511 @default.
- W3133902371 cites W2116861100 @default.
- W3133902371 cites W2121058967 @default.
- W3133902371 cites W2123716044 @default.
- W3133902371 cites W2124592697 @default.
- W3133902371 cites W2130789253 @default.
- W3133902371 cites W2150134853 @default.
- W3133902371 cites W2156379660 @default.
- W3133902371 cites W2163112044 @default.
- W3133902371 cites W2194775991 @default.
- W3133902371 cites W2273561594 @default.
- W3133902371 cites W2346276594 @default.
- W3133902371 cites W2560533888 @default.
- W3133902371 cites W2574952845 @default.
- W3133902371 cites W2618530766 @default.
- W3133902371 cites W2782977076 @default.
- W3133902371 cites W2787198218 @default.
- W3133902371 cites W2806774428 @default.
- W3133902371 cites W2900620189 @default.
- W3133902371 cites W2902719825 @default.
- W3133902371 cites W2903660960 @default.
- W3133902371 cites W2911782783 @default.
- W3133902371 cites W2928133111 @default.
- W3133902371 cites W2935732260 @default.
- W3133902371 cites W2962708058 @default.
- W3133902371 cites W2962716568 @default.
- W3133902371 cites W2962905190 @default.
- W3133902371 cites W2962956060 @default.
- W3133902371 cites W2963081790 @default.
- W3133902371 cites W2963312584 @default.
- W3133902371 cites W2963676087 @default.
- W3133902371 cites W2963676935 @default.
- W3133902371 cites W2963739249 @default.
- W3133902371 cites W2963747696 @default.
- W3133902371 cites W2964030969 @default.
- W3133902371 cites W2969940716 @default.
- W3133902371 cites W2972675027 @default.
- W3133902371 cites W2998785217 @default.
- W3133902371 cites W3006643426 @default.
- W3133902371 cites W3011730771 @default.
- W3133902371 cites W3048671742 @default.
- W3133902371 cites W3102025760 @default.
- W3133902371 cites W3103372211 @default.
- W3133902371 cites W3103586216 @default.
- W3133902371 cites W3104949790 @default.
- W3133902371 cites W3108591189 @default.
- W3133902371 cites W3144554172 @default.
- W3133902371 cites W4255949318 @default.
- W3133902371 cites W4292363360 @default.
- W3133902371 cites W4300263211 @default.
- W3133902371 cites W2891229546 @default.
- W3133902371 doi "https://doi.org/10.1109/msp.2020.3016905" @default.
- W3133902371 hasPublicationYear "2021" @default.
- W3133902371 type Work @default.
- W3133902371 sameAs 3133902371 @default.
- W3133902371 citedByCount "414" @default.
- W3133902371 countsByYear W31339023712020 @default.
- W3133902371 countsByYear W31339023712021 @default.
- W3133902371 countsByYear W31339023712022 @default.
- W3133902371 countsByYear W31339023712023 @default.
- W3133902371 crossrefType "journal-article" @default.
- W3133902371 hasAuthorship W3133902371A5005913897 @default.
- W3133902371 hasAuthorship W3133902371A5014013504 @default.
- W3133902371 hasAuthorship W3133902371A5015969128 @default.
- W3133902371 hasBestOaLocation W31339023712 @default.
- W3133902371 hasConcept C104267543 @default.
- W3133902371 hasConcept C11413529 @default.
- W3133902371 hasConcept C115961682 @default.
- W3133902371 hasConcept C153180895 @default.
- W3133902371 hasConcept C154945302 @default.
- W3133902371 hasConcept C31972630 @default.
- W3133902371 hasConcept C41008148 @default.