Matches in SemOpenAlex for { <https://semopenalex.org/work/W2028816600> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2028816600 abstract "This behavior of a constrained linear computing unit is analysed during “Hebbian” learning by gradient descent of a cost function corresponding to the sum of a variance maximization and a weight normalization term. The n-dimensional landscape of this cost function is shown to be composed of one local maximum and of n saddle points plus one global minimum aligned with the principal components of the input patterns. Furthermore, the landscape can be described in terms of hyperspheres, hypercrests, and hypervalleys associated with each of these principal components. Using this description, it is shown that the learning trajectory will converge to the global minimum of the landscape corresponding to the main principal component of the input patterns, provided some conditions on the starting weights and on the learning rate of the descent procedure. Extensions and implications of the algorithm are discussed." @default.
- W2028816600 created "2016-06-24" @default.
- W2028816600 creator A5028959656 @default.
- W2028816600 date "1991-01-01" @default.
- W2028816600 modified "2023-09-23" @default.
- W2028816600 title "CONSTRAINED HEBBIAN LEARNING: GRADIENT DESCENT TO GLOBAL MINIMA IN AN n-DIMENSIONAL LANDSCAPE" @default.
- W2028816600 doi "https://doi.org/10.1142/s0129065791000042" @default.
- W2028816600 hasPublicationYear "1991" @default.
- W2028816600 type Work @default.
- W2028816600 sameAs 2028816600 @default.
- W2028816600 citedByCount "1" @default.
- W2028816600 crossrefType "journal-article" @default.
- W2028816600 hasAuthorship W2028816600A5028959656 @default.
- W2028816600 hasConcept C111437709 @default.
- W2028816600 hasConcept C126255220 @default.
- W2028816600 hasConcept C134306372 @default.
- W2028816600 hasConcept C136886441 @default.
- W2028816600 hasConcept C144024400 @default.
- W2028816600 hasConcept C153258448 @default.
- W2028816600 hasConcept C154945302 @default.
- W2028816600 hasConcept C162324750 @default.
- W2028816600 hasConcept C186633575 @default.
- W2028816600 hasConcept C19165224 @default.
- W2028816600 hasConcept C2524010 @default.
- W2028816600 hasConcept C2681867 @default.
- W2028816600 hasConcept C27438332 @default.
- W2028816600 hasConcept C2776330181 @default.
- W2028816600 hasConcept C2777303404 @default.
- W2028816600 hasConcept C33923547 @default.
- W2028816600 hasConcept C41008148 @default.
- W2028816600 hasConcept C50522688 @default.
- W2028816600 hasConcept C50644808 @default.
- W2028816600 hasConceptScore W2028816600C111437709 @default.
- W2028816600 hasConceptScore W2028816600C126255220 @default.
- W2028816600 hasConceptScore W2028816600C134306372 @default.
- W2028816600 hasConceptScore W2028816600C136886441 @default.
- W2028816600 hasConceptScore W2028816600C144024400 @default.
- W2028816600 hasConceptScore W2028816600C153258448 @default.
- W2028816600 hasConceptScore W2028816600C154945302 @default.
- W2028816600 hasConceptScore W2028816600C162324750 @default.
- W2028816600 hasConceptScore W2028816600C186633575 @default.
- W2028816600 hasConceptScore W2028816600C19165224 @default.
- W2028816600 hasConceptScore W2028816600C2524010 @default.
- W2028816600 hasConceptScore W2028816600C2681867 @default.
- W2028816600 hasConceptScore W2028816600C27438332 @default.
- W2028816600 hasConceptScore W2028816600C2776330181 @default.
- W2028816600 hasConceptScore W2028816600C2777303404 @default.
- W2028816600 hasConceptScore W2028816600C33923547 @default.
- W2028816600 hasConceptScore W2028816600C41008148 @default.
- W2028816600 hasConceptScore W2028816600C50522688 @default.
- W2028816600 hasConceptScore W2028816600C50644808 @default.
- W2028816600 hasLocation W20288166001 @default.
- W2028816600 hasOpenAccess W2028816600 @default.
- W2028816600 hasPrimaryLocation W20288166001 @default.
- W2028816600 hasRelatedWork W1967961696 @default.
- W2028816600 hasRelatedWork W2076165463 @default.
- W2028816600 hasRelatedWork W2162160137 @default.
- W2028816600 hasRelatedWork W2591714514 @default.
- W2028816600 hasRelatedWork W2806265408 @default.
- W2028816600 hasRelatedWork W2807930578 @default.
- W2028816600 hasRelatedWork W2894604724 @default.
- W2028816600 hasRelatedWork W2896834587 @default.
- W2028816600 hasRelatedWork W2952469083 @default.
- W2028816600 hasRelatedWork W2952917720 @default.
- W2028816600 hasRelatedWork W2965025199 @default.
- W2028816600 hasRelatedWork W2971055146 @default.
- W2028816600 hasRelatedWork W3011132101 @default.
- W2028816600 hasRelatedWork W3036788601 @default.
- W2028816600 hasRelatedWork W3096414582 @default.
- W2028816600 hasRelatedWork W3104693254 @default.
- W2028816600 hasRelatedWork W3107512664 @default.
- W2028816600 hasRelatedWork W3116838285 @default.
- W2028816600 hasRelatedWork W3148518187 @default.
- W2028816600 hasRelatedWork W3201944662 @default.
- W2028816600 isParatext "false" @default.
- W2028816600 isRetracted "false" @default.
- W2028816600 magId "2028816600" @default.
- W2028816600 workType "article" @default.