FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W916919677> ?p ?o ?g. }

• W916919677 abstract "This thesis is motivated by the perspective of connecting compressed sensing and machine learning, and more particularly by the exploitation of compressed sensing techniques to reduce the cost of learning tasks. After a reminder of compressed sensing and a quick description of data analysis techniques in which similar ideas are exploited, we propose a framework for estimating probability density mixture parameters in which the training data is compressed into a fixed-size representation. We instantiate this framework on an isotropic Gaussian mixture model. This proof of concept suggests the existence of theoretical guarantees for reconstructing signals belonging to models beyond usual sparse models. We therefore study generalizations of stability results for linear inverse problems for very general models of signals. We propose conditions under which reconstruction guarantees can be given in a general framework. Finally, we consider an approximate nearest neighbor search problem exploiting signatures of the database vectors in order to save resources during the search step. In the case where the considered distance derives from a Mercer kernel, we propose to combine an explicit embedding of data followed by a signature computation step, which principally leads to a more accurate approximate search." @default.
• W916919677 created "2016-06-24" @default.
• W916919677 creator A5019490143 @default.
• W916919677 date "2014-05-13" @default.
• W916919677 modified "2023-09-25" @default.
• W916919677 title "Échantillonnage compressé et réduction de dimension pour l'apprentissage non supervisé" @default.
• W916919677 cites W1202875439 @default.
• W916919677 cites W143004564 @default.
• W916919677 cites W1485965443 @default.
• W916919677 cites W1493892051 @default.
• W916919677 cites W1502916507 @default.
• W916919677 cites W1560724230 @default.
• W916919677 cites W1568229137 @default.
• W916919677 cites W1570089119 @default.
• W916919677 cites W1591116419 @default.
• W916919677 cites W1627400044 @default.
• W916919677 cites W18046889 @default.
• W916919677 cites W1865797552 @default.
• W916919677 cites W1966385142 @default.
• W916919677 cites W1969241115 @default.
• W916919677 cites W1974466705 @default.
• W916919677 cites W1977520307 @default.
• W916919677 cites W1980911747 @default.
• W916919677 cites W1985123706 @default.
• W916919677 cites W1986736933 @default.
• W916919677 cites W1986931325 @default.
• W916919677 cites W1987040325 @default.
• W916919677 cites W1994616650 @default.
• W916919677 cites W1999352252 @default.
• W916919677 cites W2012592962 @default.
• W916919677 cites W2012833704 @default.
• W916919677 cites W2015418199 @default.
• W916919677 cites W2019741018 @default.
• W916919677 cites W2020390700 @default.
• W916919677 cites W2021302824 @default.
• W916919677 cites W2028781966 @default.
• W916919677 cites W2030449718 @default.
• W916919677 cites W2032796878 @default.
• W916919677 cites W2038276547 @default.
• W916919677 cites W2038597090 @default.
• W916919677 cites W2041101642 @default.
• W916919677 cites W2041227508 @default.
• W916919677 cites W2045983409 @default.
• W916919677 cites W2048210735 @default.
• W916919677 cites W2053075747 @default.
• W916919677 cites W2053171205 @default.
• W916919677 cites W2054010646 @default.
• W916919677 cites W2060324268 @default.
• W916919677 cites W2061375390 @default.
• W916919677 cites W2077520262 @default.
• W916919677 cites W2078397124 @default.
• W916919677 cites W2081746825 @default.
• W916919677 cites W2084363474 @default.
• W916919677 cites W2094325384 @default.
• W916919677 cites W2097323375 @default.
• W916919677 cites W2099641086 @default.
• W916919677 cites W2100875869 @default.
• W916919677 cites W2103955025 @default.
• W916919677 cites W2104608642 @default.
• W916919677 cites W2104978738 @default.
• W916919677 cites W2105877514 @default.
• W916919677 cites W2107059427 @default.
• W916919677 cites W2109235804 @default.
• W916919677 cites W2110355775 @default.
• W916919677 cites W2113651538 @default.
• W916919677 cites W2114129195 @default.
• W916919677 cites W2116148865 @default.
• W916919677 cites W2117497535 @default.
• W916919677 cites W2117756735 @default.
• W916919677 cites W2118410043 @default.
• W916919677 cites W2118550318 @default.
• W916919677 cites W2123395972 @default.
• W916919677 cites W2124455902 @default.
• W916919677 cites W2124509324 @default.
• W916919677 cites W2125378448 @default.
• W916919677 cites W2129131372 @default.
• W916919677 cites W2129638195 @default.
• W916919677 cites W2131846894 @default.
• W916919677 cites W2132234208 @default.
• W916919677 cites W2135780853 @default.
• W916919677 cites W2137198385 @default.
• W916919677 cites W2139095575 @default.
• W916919677 cites W2140089781 @default.
• W916919677 cites W2140095548 @default.
• W916919677 cites W2141433180 @default.
• W916919677 cites W2143053860 @default.
• W916919677 cites W2144902422 @default.
• W916919677 cites W2145096794 @default.
• W916919677 cites W2145962650 @default.
• W916919677 cites W2147717514 @default.
• W916919677 cites W2151103935 @default.
• W916919677 cites W2151693816 @default.
• W916919677 cites W2152356156 @default.
• W916919677 cites W2152804278 @default.
• W916919677 cites W2154172459 @default.
• W916919677 cites W2159268085 @default.
• W916919677 cites W2161581368 @default.
• W916919677 cites W2162006472 @default.
• W916919677 cites W2162451874 @default.
• W916919677 cites W2164452299 @default.

• next