Matches in SemOpenAlex for { <https://semopenalex.org/work/W2189030007> ?p ?o ?g. }
- W2189030007 abstract "A fundamental problem in machine learning research, as well as in many other disciplines, is finding a suitable representation of multivariate data, i.e. random vectors. For reasons of computational and conceptual simplicity, the representation is often sought as a linear transformation of the original data. In other words, each component of the representation is a linear combination of the original variables. Well-known linear transformation methods include principal component analysis (PCA), factor analysis, and projection pursuit. In this thesis, we consider two popular and widely used techniques: independent component analysis (ICA) and nonnegative matrix factorization (NMF). ICA is a statistical method in which the goal is to find a linear representation of nongaussian data so that the components are statistically independent, or as independent as possible. Such a representation seems to capture the essential structure of the data in many applications, including feature extraction and signal separation. Starting from ICA, several methods of estimating the latent structure in different problem settings are derived and presented in this thesis. FastICA as one of most efficient and popular ICA algorithms has been reviewed and discussed. Its local and global convergence and statistical behavior have been further studied. A nonnegative FastICA algorithm is also given in this thesis. Nonnegative matrix factorization is a recently developed technique for finding parts-based, linear representations of non-negative data. It is a method for dimensionality reduction that respects the nonnegativity of the input data while constructing a low-dimensional approximation. The non-negativity constraints make the representation purely additive (allowing no subtractions), in contrast to many other linear representations such as principal component analysis and independent component analysis. A literature survey of Nonnegative matrix factorization is given in this thesis, and a novel method called Projective Nonnegative matrix factorization (P-NMF) and its applications are provided." @default.
- W2189030007 created "2016-06-24" @default.
- W2189030007 creator A5057988200 @default.
- W2189030007 date "2009-01-01" @default.
- W2189030007 modified "2023-09-23" @default.
- W2189030007 title "Advances in independent component analysis and nonnegative matrix factorization" @default.
- W2189030007 cites W1488854477 @default.
- W2189030007 cites W1491770470 @default.
- W2189030007 cites W1500921805 @default.
- W2189030007 cites W1514159701 @default.
- W2189030007 cites W1520580733 @default.
- W2189030007 cites W1520758132 @default.
- W2189030007 cites W1530896671 @default.
- W2189030007 cites W1533423434 @default.
- W2189030007 cites W1544423579 @default.
- W2189030007 cites W1547060653 @default.
- W2189030007 cites W1548802052 @default.
- W2189030007 cites W1551509424 @default.
- W2189030007 cites W1565719317 @default.
- W2189030007 cites W1591750703 @default.
- W2189030007 cites W1594523130 @default.
- W2189030007 cites W1604952736 @default.
- W2189030007 cites W1629332708 @default.
- W2189030007 cites W1661328078 @default.
- W2189030007 cites W1667165204 @default.
- W2189030007 cites W1790954942 @default.
- W2189030007 cites W1827228761 @default.
- W2189030007 cites W1902027874 @default.
- W2189030007 cites W1904809838 @default.
- W2189030007 cites W1914599625 @default.
- W2189030007 cites W1964900243 @default.
- W2189030007 cites W1964909831 @default.
- W2189030007 cites W1970789124 @default.
- W2189030007 cites W1971104076 @default.
- W2189030007 cites W1974388905 @default.
- W2189030007 cites W1976045444 @default.
- W2189030007 cites W1976391658 @default.
- W2189030007 cites W1977067929 @default.
- W2189030007 cites W1980793158 @default.
- W2189030007 cites W1981984445 @default.
- W2189030007 cites W1984035260 @default.
- W2189030007 cites W1990007244 @default.
- W2189030007 cites W1991380130 @default.
- W2189030007 cites W1995714592 @default.
- W2189030007 cites W2002519017 @default.
- W2189030007 cites W2012470056 @default.
- W2189030007 cites W2017288758 @default.
- W2189030007 cites W2019502123 @default.
- W2189030007 cites W2022242697 @default.
- W2189030007 cites W2022851313 @default.
- W2189030007 cites W2030308473 @default.
- W2189030007 cites W2033693394 @default.
- W2189030007 cites W2035330847 @default.
- W2189030007 cites W2036488048 @default.
- W2189030007 cites W2050583479 @default.
- W2189030007 cites W2050616618 @default.
- W2189030007 cites W2055070149 @default.
- W2189030007 cites W2056857971 @default.
- W2189030007 cites W2059745395 @default.
- W2189030007 cites W2064690543 @default.
- W2189030007 cites W2066808305 @default.
- W2189030007 cites W206759535 @default.
- W2189030007 cites W2069234701 @default.
- W2189030007 cites W2070371729 @default.
- W2189030007 cites W2075665712 @default.
- W2189030007 cites W2079196839 @default.
- W2189030007 cites W2082599080 @default.
- W2189030007 cites W2085936845 @default.
- W2189030007 cites W2089079408 @default.
- W2189030007 cites W2091909564 @default.
- W2189030007 cites W2092423825 @default.
- W2189030007 cites W2093551558 @default.
- W2189030007 cites W2094810662 @default.
- W2189030007 cites W2096504408 @default.
- W2189030007 cites W2099741732 @default.
- W2189030007 cites W2100493539 @default.
- W2189030007 cites W2101933716 @default.
- W2189030007 cites W2104298926 @default.
- W2189030007 cites W2104457585 @default.
- W2189030007 cites W2106582496 @default.
- W2189030007 cites W2106771705 @default.
- W2189030007 cites W2108373649 @default.
- W2189030007 cites W2108384452 @default.
- W2189030007 cites W2110096996 @default.
- W2189030007 cites W2113359929 @default.
- W2189030007 cites W2114013702 @default.
- W2189030007 cites W2114018052 @default.
- W2189030007 cites W2114968688 @default.
- W2189030007 cites W2115562224 @default.
- W2189030007 cites W2116914769 @default.
- W2189030007 cites W2117824861 @default.
- W2189030007 cites W2118718620 @default.
- W2189030007 cites W2118804867 @default.
- W2189030007 cites W2120978234 @default.
- W2189030007 cites W2124486835 @default.
- W2189030007 cites W2124847261 @default.
- W2189030007 cites W2125173990 @default.
- W2189030007 cites W2125604471 @default.
- W2189030007 cites W2127877256 @default.
- W2189030007 cites W2130789253 @default.