Matches in SemOpenAlex for { <https://semopenalex.org/work/W2016573670> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2016573670 abstract "Recently, various dimensionality reduction approaches have been proposed as alternatives to PCA or LDA. These improved approaches do not rely on a linearity assumption, and are hence capable of discovering more complex embeddings within different regions of the data sets. Despite their success on artificial datasets, it is not straightforward to predict which technique is the most appropriate for a given real dataset. In this paper, we empirically evaluate recent techniques on two real audio use cases: musical instrument loops used in music production and sound effects used in sound editing. ISOMAP and t-SNE are being compared to PCA in a visualization problem, where we end up with a two-dimensional view. Various evaluation measures are used: classification performance, as well as trustworthiness/continuity assessing the preservation of neighborhoods. Although PCA and ISOMAP can yield good continuity performance even locally (samples in the original space remain close-by in the low-dimensional one), they fail to preserve the structure of the data well enough to ensure that distinct subgroups remain separate in the visualization. We show that t-SNE presents the best performance, and can even be beneficial as a pre-processing stage for improving classification when the amount of labeled data is low." @default.
- W2016573670 created "2016-06-24" @default.
- W2016573670 creator A5023953972 @default.
- W2016573670 creator A5034678163 @default.
- W2016573670 creator A5078552580 @default.
- W2016573670 creator A5083563222 @default.
- W2016573670 date "2013-07-01" @default.
- W2016573670 modified "2023-09-27" @default.
- W2016573670 title "Nonlinear dimensionality reduction approaches applied to music and textural sounds" @default.
- W2016573670 cites W1742512077 @default.
- W2016573670 cites W2001141328 @default.
- W2016573670 cites W2043508111 @default.
- W2016573670 cites W2080400971 @default.
- W2016573670 cites W2118527389 @default.
- W2016573670 cites W2141317097 @default.
- W2016573670 doi "https://doi.org/10.1109/icme.2013.6607550" @default.
- W2016573670 hasPublicationYear "2013" @default.
- W2016573670 type Work @default.
- W2016573670 sameAs 2016573670 @default.
- W2016573670 citedByCount "7" @default.
- W2016573670 countsByYear W20165736702013 @default.
- W2016573670 countsByYear W20165736702014 @default.
- W2016573670 countsByYear W20165736702017 @default.
- W2016573670 countsByYear W20165736702020 @default.
- W2016573670 countsByYear W20165736702023 @default.
- W2016573670 crossrefType "proceedings-article" @default.
- W2016573670 hasAuthorship W2016573670A5023953972 @default.
- W2016573670 hasAuthorship W2016573670A5034678163 @default.
- W2016573670 hasAuthorship W2016573670A5078552580 @default.
- W2016573670 hasAuthorship W2016573670A5083563222 @default.
- W2016573670 hasConcept C111030470 @default.
- W2016573670 hasConcept C111335779 @default.
- W2016573670 hasConcept C119857082 @default.
- W2016573670 hasConcept C124101348 @default.
- W2016573670 hasConcept C127220857 @default.
- W2016573670 hasConcept C13895895 @default.
- W2016573670 hasConcept C151876577 @default.
- W2016573670 hasConcept C153180895 @default.
- W2016573670 hasConcept C154945302 @default.
- W2016573670 hasConcept C172367668 @default.
- W2016573670 hasConcept C2524010 @default.
- W2016573670 hasConcept C2778626561 @default.
- W2016573670 hasConcept C28490314 @default.
- W2016573670 hasConcept C33923547 @default.
- W2016573670 hasConcept C36464697 @default.
- W2016573670 hasConcept C41008148 @default.
- W2016573670 hasConcept C64922751 @default.
- W2016573670 hasConcept C70518039 @default.
- W2016573670 hasConceptScore W2016573670C111030470 @default.
- W2016573670 hasConceptScore W2016573670C111335779 @default.
- W2016573670 hasConceptScore W2016573670C119857082 @default.
- W2016573670 hasConceptScore W2016573670C124101348 @default.
- W2016573670 hasConceptScore W2016573670C127220857 @default.
- W2016573670 hasConceptScore W2016573670C13895895 @default.
- W2016573670 hasConceptScore W2016573670C151876577 @default.
- W2016573670 hasConceptScore W2016573670C153180895 @default.
- W2016573670 hasConceptScore W2016573670C154945302 @default.
- W2016573670 hasConceptScore W2016573670C172367668 @default.
- W2016573670 hasConceptScore W2016573670C2524010 @default.
- W2016573670 hasConceptScore W2016573670C2778626561 @default.
- W2016573670 hasConceptScore W2016573670C28490314 @default.
- W2016573670 hasConceptScore W2016573670C33923547 @default.
- W2016573670 hasConceptScore W2016573670C36464697 @default.
- W2016573670 hasConceptScore W2016573670C41008148 @default.
- W2016573670 hasConceptScore W2016573670C64922751 @default.
- W2016573670 hasConceptScore W2016573670C70518039 @default.
- W2016573670 hasLocation W20165736701 @default.
- W2016573670 hasOpenAccess W2016573670 @default.
- W2016573670 hasPrimaryLocation W20165736701 @default.
- W2016573670 hasRelatedWork W2068738617 @default.
- W2016573670 hasRelatedWork W2080051048 @default.
- W2016573670 hasRelatedWork W2107154991 @default.
- W2016573670 hasRelatedWork W2130883347 @default.
- W2016573670 hasRelatedWork W2139206098 @default.
- W2016573670 hasRelatedWork W2148415967 @default.
- W2016573670 hasRelatedWork W2166963679 @default.
- W2016573670 hasRelatedWork W2244615982 @default.
- W2016573670 hasRelatedWork W2380996235 @default.
- W2016573670 hasRelatedWork W2943319439 @default.
- W2016573670 isParatext "false" @default.
- W2016573670 isRetracted "false" @default.
- W2016573670 magId "2016573670" @default.
- W2016573670 workType "article" @default.