Matches in SemOpenAlex for { <https://semopenalex.org/work/W2170052858> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2170052858 endingPage "29" @default.
- W2170052858 startingPage "1" @default.
- W2170052858 abstract "The Minimum Description Length (MDL) principle is solidly based on a provably ideal method of inference using Kolmogorov complexity. We test how the theory behaves in practice on a general problem in model selection: that of learning the best model granularity. The performance of a model depends critically on the granularity, for example the choice of precision of the parameters. Too high precision generally involves modeling of accidental noise and too low precision may lead to confusion of models that should be distinguished. This precision is often determined ad hoc. In MDL the best model is the one that most compresses a two-part code of the data set: this embodies “Occam's Razor”. In two quite different experimental settings the theoretical value determined using MDL coincides with the best value found experimentally. In the first experiment the task is to recognize isolated handwritten characters in one subject's handwriting, irrespective of size and orientation. Based on a new modification of elastic matching, using multiple prototypes per character, the optimal prediction rate is predicted for the learned parameter (length of sampling interval) considered most likely by MDL, which is shown to coincide with the best value found experimentally. In the second experiment the task is to model a robot arm with two degrees of freedom using a three layer feed-forward neural network where we need to determine the number of nodes in the hidden layer giving best modeling performance. The optimal model (the one that extrapolizes best on unseen examples) is predicted for the number of nodes in the hidden layer considered most likely by MDL, which again is found to coincide with the best value found experimentally." @default.
- W2170052858 created "2016-06-24" @default.
- W2170052858 creator A5029628745 @default.
- W2170052858 creator A5078578462 @default.
- W2170052858 creator A5086623091 @default.
- W2170052858 date "2000-08-01" @default.
- W2170052858 modified "2023-10-14" @default.
- W2170052858 title "Applying MDL to learn best model granularity" @default.
- W2170052858 cites W1983661866 @default.
- W2170052858 cites W1992958898 @default.
- W2170052858 cites W2054658115 @default.
- W2170052858 cites W2057211203 @default.
- W2170052858 cites W2062361515 @default.
- W2170052858 cites W2065734030 @default.
- W2170052858 cites W2067580807 @default.
- W2170052858 cites W2075569940 @default.
- W2170052858 cites W2090547656 @default.
- W2170052858 cites W2102098892 @default.
- W2170052858 cites W2110381504 @default.
- W2170052858 cites W2111051539 @default.
- W2170052858 cites W2113832384 @default.
- W2170052858 cites W2117072511 @default.
- W2170052858 cites W2132119275 @default.
- W2170052858 cites W2172780573 @default.
- W2170052858 cites W4213350211 @default.
- W2170052858 cites W4238893454 @default.
- W2170052858 doi "https://doi.org/10.1016/s0004-3702(00)00034-5" @default.
- W2170052858 hasPublicationYear "2000" @default.
- W2170052858 type Work @default.
- W2170052858 sameAs 2170052858 @default.
- W2170052858 citedByCount "45" @default.
- W2170052858 countsByYear W21700528582012 @default.
- W2170052858 countsByYear W21700528582013 @default.
- W2170052858 countsByYear W21700528582017 @default.
- W2170052858 crossrefType "journal-article" @default.
- W2170052858 hasAuthorship W2170052858A5029628745 @default.
- W2170052858 hasAuthorship W2170052858A5078578462 @default.
- W2170052858 hasAuthorship W2170052858A5086623091 @default.
- W2170052858 hasBestOaLocation W21700528582 @default.
- W2170052858 hasConcept C111919701 @default.
- W2170052858 hasConcept C11413529 @default.
- W2170052858 hasConcept C153180895 @default.
- W2170052858 hasConcept C154945302 @default.
- W2170052858 hasConcept C177264268 @default.
- W2170052858 hasConcept C177774035 @default.
- W2170052858 hasConcept C199360897 @default.
- W2170052858 hasConcept C33923547 @default.
- W2170052858 hasConcept C41008148 @default.
- W2170052858 hasConcept C87465248 @default.
- W2170052858 hasConcept C93959086 @default.
- W2170052858 hasConceptScore W2170052858C111919701 @default.
- W2170052858 hasConceptScore W2170052858C11413529 @default.
- W2170052858 hasConceptScore W2170052858C153180895 @default.
- W2170052858 hasConceptScore W2170052858C154945302 @default.
- W2170052858 hasConceptScore W2170052858C177264268 @default.
- W2170052858 hasConceptScore W2170052858C177774035 @default.
- W2170052858 hasConceptScore W2170052858C199360897 @default.
- W2170052858 hasConceptScore W2170052858C33923547 @default.
- W2170052858 hasConceptScore W2170052858C41008148 @default.
- W2170052858 hasConceptScore W2170052858C87465248 @default.
- W2170052858 hasConceptScore W2170052858C93959086 @default.
- W2170052858 hasIssue "1-2" @default.
- W2170052858 hasLocation W21700528581 @default.
- W2170052858 hasLocation W21700528582 @default.
- W2170052858 hasOpenAccess W2170052858 @default.
- W2170052858 hasPrimaryLocation W21700528581 @default.
- W2170052858 hasRelatedWork W150710766 @default.
- W2170052858 hasRelatedWork W1559625850 @default.
- W2170052858 hasRelatedWork W1973600191 @default.
- W2170052858 hasRelatedWork W2037989911 @default.
- W2170052858 hasRelatedWork W2046229974 @default.
- W2170052858 hasRelatedWork W2148249824 @default.
- W2170052858 hasRelatedWork W23219711 @default.
- W2170052858 hasRelatedWork W2949276475 @default.
- W2170052858 hasRelatedWork W2987333292 @default.
- W2170052858 hasRelatedWork W4285790282 @default.
- W2170052858 hasVolume "121" @default.
- W2170052858 isParatext "false" @default.
- W2170052858 isRetracted "false" @default.
- W2170052858 magId "2170052858" @default.
- W2170052858 workType "article" @default.