Matches in SemOpenAlex for { <https://semopenalex.org/work/W85401708> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W85401708 abstract "Fuzzy ART and Fuzzy ARTMAP are two prominent neural network architectures based on the principles of Grossberg's Adaptive Resonance Theory (ART). While the former architecture employs unsupervised learning to perform clustering tasks, the latter one associates clusters belonging to an input and output domain in a supervised manner. As a special case, Fuzzy ARTMAP can also be used as a classifier. Both networks implement an exemplar-based learning method and summarize training patterns into categories (exemplars), whose geometric representation are hyper-rectangles embedded in the input domain. We introduce two novel ART-based neural network architectures, namely Ellipsoid ART and Ellipsoid ARTMAP, which utilize hyper-ellipsoids for category representation. We have designed these two architectures, so that they share all essential properties and characteristics of their Fuzzy counterparts. Of foremost importance, they are capable of fast, stable learning, meaning that learning completes in a finite number of steps. We also present selected experimental results that illustrate the potential of Ellipsoid ARTMAP to successfully perform classification tasks by exhibiting high prediction accuracy, while maintaining a relatively small number of categories. Next, we introduce category regions as novel concepts that enrich the geometric facet of Fuzzy ART and Fuzzy ARTMAP operations. Their definition stems from the geometric interpretation of two particular conditions that are examined, in order to assess the degree to which an input pattern matches the characteristics of an existing category already memorized by a Fuzzy ART or Fuzzy ARTMAP network. Apart from aiding us in gaining a clearer understanding of the networks' training and performance phases, based on the regions' properties we arrive at several results that are primarily of theoretical interest. Furthermore, due to the underlying similarity, all these results are shown to be applicable to Ellipsoid ART and Ellipsoid ARTMAP as well." @default.
- W85401708 created "2016-06-24" @default.
- W85401708 creator A5025334497 @default.
- W85401708 creator A5036799400 @default.
- W85401708 date "2001-01-01" @default.
- W85401708 modified "2023-10-11" @default.
- W85401708 title "Novel approaches in adaptive resonance theory for machine learning" @default.
- W85401708 hasPublicationYear "2001" @default.
- W85401708 type Work @default.
- W85401708 sameAs 85401708 @default.
- W85401708 citedByCount "17" @default.
- W85401708 crossrefType "journal-article" @default.
- W85401708 hasAuthorship W85401708A5025334497 @default.
- W85401708 hasAuthorship W85401708A5036799400 @default.
- W85401708 hasConcept C115755159 @default.
- W85401708 hasConcept C119857082 @default.
- W85401708 hasConcept C121332964 @default.
- W85401708 hasConcept C1276947 @default.
- W85401708 hasConcept C153180895 @default.
- W85401708 hasConcept C154945302 @default.
- W85401708 hasConcept C17744445 @default.
- W85401708 hasConcept C199539241 @default.
- W85401708 hasConcept C2776359362 @default.
- W85401708 hasConcept C41008148 @default.
- W85401708 hasConcept C42011625 @default.
- W85401708 hasConcept C50644808 @default.
- W85401708 hasConcept C57489055 @default.
- W85401708 hasConcept C58166 @default.
- W85401708 hasConcept C73555534 @default.
- W85401708 hasConcept C94625758 @default.
- W85401708 hasConcept C95623464 @default.
- W85401708 hasConceptScore W85401708C115755159 @default.
- W85401708 hasConceptScore W85401708C119857082 @default.
- W85401708 hasConceptScore W85401708C121332964 @default.
- W85401708 hasConceptScore W85401708C1276947 @default.
- W85401708 hasConceptScore W85401708C153180895 @default.
- W85401708 hasConceptScore W85401708C154945302 @default.
- W85401708 hasConceptScore W85401708C17744445 @default.
- W85401708 hasConceptScore W85401708C199539241 @default.
- W85401708 hasConceptScore W85401708C2776359362 @default.
- W85401708 hasConceptScore W85401708C41008148 @default.
- W85401708 hasConceptScore W85401708C42011625 @default.
- W85401708 hasConceptScore W85401708C50644808 @default.
- W85401708 hasConceptScore W85401708C57489055 @default.
- W85401708 hasConceptScore W85401708C58166 @default.
- W85401708 hasConceptScore W85401708C73555534 @default.
- W85401708 hasConceptScore W85401708C94625758 @default.
- W85401708 hasConceptScore W85401708C95623464 @default.
- W85401708 hasLocation W854017081 @default.
- W85401708 hasOpenAccess W85401708 @default.
- W85401708 hasPrimaryLocation W854017081 @default.
- W85401708 hasRelatedWork W134309601 @default.
- W85401708 hasRelatedWork W155943900 @default.
- W85401708 hasRelatedWork W1594031697 @default.
- W85401708 hasRelatedWork W1797753341 @default.
- W85401708 hasRelatedWork W1871379767 @default.
- W85401708 hasRelatedWork W1914318842 @default.
- W85401708 hasRelatedWork W1919642887 @default.
- W85401708 hasRelatedWork W1979828500 @default.
- W85401708 hasRelatedWork W1982610692 @default.
- W85401708 hasRelatedWork W2005312922 @default.
- W85401708 hasRelatedWork W2012611887 @default.
- W85401708 hasRelatedWork W2034526008 @default.
- W85401708 hasRelatedWork W2051504418 @default.
- W85401708 hasRelatedWork W2083909184 @default.
- W85401708 hasRelatedWork W2084812512 @default.
- W85401708 hasRelatedWork W2105333549 @default.
- W85401708 hasRelatedWork W2109731247 @default.
- W85401708 hasRelatedWork W2166280719 @default.
- W85401708 hasRelatedWork W2209948639 @default.
- W85401708 hasRelatedWork W2484357222 @default.
- W85401708 isParatext "false" @default.
- W85401708 isRetracted "false" @default.
- W85401708 magId "85401708" @default.
- W85401708 workType "article" @default.