FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949271011> ?p ?o ?g. }

• W2949271011 endingPage "15" @default.
• W2949271011 startingPage "1" @default.
• W2949271011 abstract "A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems, however, the label information is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerful methods exist for extracting the cluster structure in data, they typically do not answer the question why a certain data point has been assigned to a given cluster. We propose a new framework that can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based on the novel insight that clustering models can be rewritten as neural networks-or neuralized. Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extract novel insights from the analyzed data and representations." @default.
• W2949271011 created "2019-06-27" @default.
• W2949271011 creator A5009868884 @default.
• W2949271011 creator A5016979661 @default.
• W2949271011 creator A5018153290 @default.
• W2949271011 creator A5026240645 @default.
• W2949271011 creator A5026451495 @default.
• W2949271011 creator A5043725008 @default.
• W2949271011 date "2022-01-01" @default.
• W2949271011 modified "2023-10-14" @default.
• W2949271011 title "From Clustering to Cluster Explanations via Neural Networks" @default.
• W2949271011 cites W122624798 @default.
• W2949271011 cites W1480376833 @default.
• W2949271011 cites W1504118426 @default.
• W2949271011 cites W1532325895 @default.
• W2949271011 cites W1560724230 @default.
• W2949271011 cites W1585535067 @default.
• W2949271011 cites W1617495083 @default.
• W2949271011 cites W1673310716 @default.
• W2949271011 cites W1686810756 @default.
• W2949271011 cites W1787224781 @default.
• W2949271011 cites W1849277567 @default.
• W2949271011 cites W1967639437 @default.
• W2949271011 cites W1986007546 @default.
• W2949271011 cites W1992419399 @default.
• W2949271011 cites W2011430131 @default.
• W2949271011 cites W2016381774 @default.
• W2949271011 cites W2042340900 @default.
• W2949271011 cites W2076572706 @default.
• W2949271011 cites W2077990749 @default.
• W2949271011 cites W2088032561 @default.
• W2949271011 cites W2096152098 @default.
• W2949271011 cites W2108643617 @default.
• W2949271011 cites W2113076747 @default.
• W2949271011 cites W2116360511 @default.
• W2949271011 cites W2121947440 @default.
• W2949271011 cites W2127218421 @default.
• W2949271011 cites W2129066856 @default.
• W2949271011 cites W2129932701 @default.
• W2949271011 cites W2135000328 @default.
• W2949271011 cites W2141012957 @default.
• W2949271011 cites W2153233077 @default.
• W2949271011 cites W2164753344 @default.
• W2949271011 cites W2165874743 @default.
• W2949271011 cites W2171009857 @default.
• W2949271011 cites W2195388612 @default.
• W2949271011 cites W2221409856 @default.
• W2949271011 cites W2282821441 @default.
• W2949271011 cites W2418098761 @default.
• W2949271011 cites W2497735908 @default.
• W2949271011 cites W2594633041 @default.
• W2949271011 cites W2605409611 @default.
• W2949271011 cites W2657631929 @default.
• W2949271011 cites W2741040846 @default.
• W2949271011 cites W2776207810 @default.
• W2949271011 cites W2785760873 @default.
• W2949271011 cites W2804236575 @default.
• W2949271011 cites W2883725317 @default.
• W2949271011 cites W2892171547 @default.
• W2949271011 cites W2917254586 @default.
• W2949271011 cites W2950577311 @default.
• W2949271011 cites W2952505933 @default.
• W2949271011 cites W2962858109 @default.
• W2949271011 cites W2963081790 @default.
• W2949271011 cites W2964045325 @default.
• W2949271011 cites W2964073283 @default.
• W2949271011 cites W2964074409 @default.
• W2949271011 cites W3100711616 @default.
• W2949271011 doi "https://doi.org/10.1109/tnnls.2022.3185901" @default.
• W2949271011 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35797317" @default.
• W2949271011 hasPublicationYear "2022" @default.
• W2949271011 type Work @default.
• W2949271011 sameAs 2949271011 @default.
• W2949271011 citedByCount "26" @default.
• W2949271011 countsByYear W29492710112020 @default.
• W2949271011 countsByYear W29492710112021 @default.
• W2949271011 countsByYear W29492710112022 @default.
• W2949271011 countsByYear W29492710112023 @default.
• W2949271011 crossrefType "journal-article" @default.
• W2949271011 hasAuthorship W2949271011A5009868884 @default.
• W2949271011 hasAuthorship W2949271011A5016979661 @default.
• W2949271011 hasAuthorship W2949271011A5018153290 @default.
• W2949271011 hasAuthorship W2949271011A5026240645 @default.
• W2949271011 hasAuthorship W2949271011A5026451495 @default.
• W2949271011 hasAuthorship W2949271011A5043725008 @default.
• W2949271011 hasBestOaLocation W29492710111 @default.
• W2949271011 hasConcept C119857082 @default.
• W2949271011 hasConcept C124101348 @default.
• W2949271011 hasConcept C154945302 @default.
• W2949271011 hasConcept C164866538 @default.
• W2949271011 hasConcept C199360897 @default.
• W2949271011 hasConcept C202444582 @default.
• W2949271011 hasConcept C2524010 @default.
• W2949271011 hasConcept C28719098 @default.
• W2949271011 hasConcept C33923547 @default.
• W2949271011 hasConcept C41008148 @default.
• W2949271011 hasConcept C50644808 @default.
• W2949271011 hasConcept C73555534 @default.

• next