Matches in SemOpenAlex for { <https://semopenalex.org/work/W2956312897> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2956312897 abstract "This thesis is devoted to geometric methods in optimization, learning and neural networks. In many problems of (supervised and unsupervised) learning, pattern recognition, and clustering there is a need to take into account the internal (intrinsic) structure of the underlying space, which is not necessary Euclidean. For Riemannian manifolds we construct computational algorithms for Newton method, conjugate-gradient methods, and some non-smooth optimization methods like the r-algorithm. For this purpose we develop methods for geodesic calculation in submanifolds based on Hamilton equations and symplectic integration. Then we construct a new type of neural associative memory capable of unsupervised learning and clustering. Its learning is based on generalized averaging over Grassmann manifolds. Further extension of this memory involves implicit space transformation and kernel machines. Also we consider geometric algorithms for signal processing and adaptive filtering. Proposed methods are tested for academic examples as well as real-life problems of image recognition and signal processing. Application of proposed neural networks is demonstrated for a complete real-life project of chemical image recognition (electronic nose)." @default.
- W2956312897 created "2019-07-23" @default.
- W2956312897 creator A5088754301 @default.
- W2956312897 date "2007-07-13" @default.
- W2956312897 modified "2023-09-25" @default.
- W2956312897 title "Geometric Methods in Learning and Memory" @default.
- W2956312897 cites W133757099 @default.
- W2956312897 cites W1485231155 @default.
- W2956312897 cites W1491663334 @default.
- W2956312897 cites W16592970 @default.
- W2956312897 cites W1742709735 @default.
- W2956312897 cites W1847820974 @default.
- W2956312897 cites W1874501052 @default.
- W2956312897 cites W1875759270 @default.
- W2956312897 cites W1917244711 @default.
- W2956312897 cites W1983894121 @default.
- W2956312897 cites W1993582230 @default.
- W2956312897 cites W2014154724 @default.
- W2956312897 cites W2025347688 @default.
- W2956312897 cites W2027559291 @default.
- W2956312897 cites W2033788889 @default.
- W2956312897 cites W2045512849 @default.
- W2956312897 cites W2047278710 @default.
- W2956312897 cites W2048401130 @default.
- W2956312897 cites W2054749664 @default.
- W2956312897 cites W2066145470 @default.
- W2956312897 cites W2093879739 @default.
- W2956312897 cites W2123208606 @default.
- W2956312897 cites W2126479355 @default.
- W2956312897 cites W2128084896 @default.
- W2956312897 cites W2143199409 @default.
- W2956312897 cites W2170925765 @default.
- W2956312897 cites W2276252907 @default.
- W2956312897 cites W2912889105 @default.
- W2956312897 cites W3000625067 @default.
- W2956312897 hasPublicationYear "2007" @default.
- W2956312897 type Work @default.
- W2956312897 sameAs 2956312897 @default.
- W2956312897 citedByCount "0" @default.
- W2956312897 crossrefType "dissertation" @default.
- W2956312897 hasAuthorship W2956312897A5088754301 @default.
- W2956312897 hasConcept C11413529 @default.
- W2956312897 hasConcept C153180895 @default.
- W2956312897 hasConcept C154945302 @default.
- W2956312897 hasConcept C165818556 @default.
- W2956312897 hasConcept C2524010 @default.
- W2956312897 hasConcept C33923547 @default.
- W2956312897 hasConcept C41008148 @default.
- W2956312897 hasConcept C50644808 @default.
- W2956312897 hasConcept C53442348 @default.
- W2956312897 hasConcept C73555534 @default.
- W2956312897 hasConcept C8038995 @default.
- W2956312897 hasConceptScore W2956312897C11413529 @default.
- W2956312897 hasConceptScore W2956312897C153180895 @default.
- W2956312897 hasConceptScore W2956312897C154945302 @default.
- W2956312897 hasConceptScore W2956312897C165818556 @default.
- W2956312897 hasConceptScore W2956312897C2524010 @default.
- W2956312897 hasConceptScore W2956312897C33923547 @default.
- W2956312897 hasConceptScore W2956312897C41008148 @default.
- W2956312897 hasConceptScore W2956312897C50644808 @default.
- W2956312897 hasConceptScore W2956312897C53442348 @default.
- W2956312897 hasConceptScore W2956312897C73555534 @default.
- W2956312897 hasConceptScore W2956312897C8038995 @default.
- W2956312897 hasLocation W29563128971 @default.
- W2956312897 hasOpenAccess W2956312897 @default.
- W2956312897 hasPrimaryLocation W29563128971 @default.
- W2956312897 hasRelatedWork W142815271 @default.
- W2956312897 hasRelatedWork W1537216475 @default.
- W2956312897 hasRelatedWork W1561280145 @default.
- W2956312897 hasRelatedWork W1938927796 @default.
- W2956312897 hasRelatedWork W1986362968 @default.
- W2956312897 hasRelatedWork W2013436814 @default.
- W2956312897 hasRelatedWork W2120368313 @default.
- W2956312897 hasRelatedWork W2126017757 @default.
- W2956312897 hasRelatedWork W2141830256 @default.
- W2956312897 hasRelatedWork W2149338181 @default.
- W2956312897 hasRelatedWork W2167604630 @default.
- W2956312897 hasRelatedWork W2783160710 @default.
- W2956312897 hasRelatedWork W2950738010 @default.
- W2956312897 hasRelatedWork W2951316237 @default.
- W2956312897 hasRelatedWork W2977511996 @default.
- W2956312897 hasRelatedWork W3045840171 @default.
- W2956312897 hasRelatedWork W3046455422 @default.
- W2956312897 hasRelatedWork W3102156899 @default.
- W2956312897 hasRelatedWork W3127442541 @default.
- W2956312897 hasRelatedWork W3208085809 @default.
- W2956312897 isParatext "false" @default.
- W2956312897 isRetracted "false" @default.
- W2956312897 magId "2956312897" @default.
- W2956312897 workType "dissertation" @default.