Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912981918> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2912981918 endingPage "42" @default.
- W2912981918 startingPage "18" @default.
- W2912981918 abstract "Abstract AI systems are usually evaluated on a range of problem instances and compared to other AI systems that use different strategies. These instances are rarely independent. Machine learning, and supervised learning in particular, is a very good example of this. Given a machine learning model, its behaviour for a single instance cannot be understood in isolation but rather in relation to the rest of the data distribution or dataset. In a dual way, the results of one machine learning model for an instance can be analysed in comparison to other models. While this analysis is relative to a population or distribution of models, it can give much more insight than an isolated analysis. Item response theory (IRT) combines this duality between items and respondents to extract latent variables of the items (such as discrimination or difficulty) and the respondents (such as ability). IRT can be adapted to the analysis of machine learning experiments (and by extension to any other artificial intelligence experiments). In this paper, we see that IRT suits classification tasks perfectly, where instances correspond to items and classifiers correspond to respondents. We perform a series of experiments with a range of datasets and classification methods to fully understand what the IRT parameters such as discrimination, difficulty and guessing mean for classification instances (and their relation to instance hardness measures) and how the estimated classifier ability can be used to compare classifier performance in a different way through classifier characteristic curves." @default.
- W2912981918 created "2019-02-21" @default.
- W2912981918 creator A5029864546 @default.
- W2912981918 creator A5051725651 @default.
- W2912981918 creator A5062999560 @default.
- W2912981918 creator A5083998049 @default.
- W2912981918 date "2019-06-01" @default.
- W2912981918 modified "2023-10-12" @default.
- W2912981918 title "Item response theory in AI: Analysing machine learning classifiers at the instance level" @default.
- W2912981918 cites W1680939745 @default.
- W2912981918 cites W1919216659 @default.
- W2912981918 cites W2011762057 @default.
- W2912981918 cites W2022477494 @default.
- W2912981918 cites W2040884411 @default.
- W2912981918 cites W2083265890 @default.
- W2912981918 cites W2116825089 @default.
- W2912981918 cites W2132862423 @default.
- W2912981918 cites W2137130182 @default.
- W2912981918 cites W2147148915 @default.
- W2912981918 cites W2511953903 @default.
- W2912981918 cites W2538262060 @default.
- W2912981918 cites W2914775474 @default.
- W2912981918 doi "https://doi.org/10.1016/j.artint.2018.09.004" @default.
- W2912981918 hasPublicationYear "2019" @default.
- W2912981918 type Work @default.
- W2912981918 sameAs 2912981918 @default.
- W2912981918 citedByCount "45" @default.
- W2912981918 countsByYear W29129819182018 @default.
- W2912981918 countsByYear W29129819182019 @default.
- W2912981918 countsByYear W29129819182020 @default.
- W2912981918 countsByYear W29129819182021 @default.
- W2912981918 countsByYear W29129819182022 @default.
- W2912981918 countsByYear W29129819182023 @default.
- W2912981918 crossrefType "journal-article" @default.
- W2912981918 hasAuthorship W2912981918A5029864546 @default.
- W2912981918 hasAuthorship W2912981918A5051725651 @default.
- W2912981918 hasAuthorship W2912981918A5062999560 @default.
- W2912981918 hasAuthorship W2912981918A5083998049 @default.
- W2912981918 hasBestOaLocation W29129819181 @default.
- W2912981918 hasConcept C105795698 @default.
- W2912981918 hasConcept C119857082 @default.
- W2912981918 hasConcept C154945302 @default.
- W2912981918 hasConcept C171606756 @default.
- W2912981918 hasConcept C19875794 @default.
- W2912981918 hasConcept C33923547 @default.
- W2912981918 hasConcept C41008148 @default.
- W2912981918 hasConceptScore W2912981918C105795698 @default.
- W2912981918 hasConceptScore W2912981918C119857082 @default.
- W2912981918 hasConceptScore W2912981918C154945302 @default.
- W2912981918 hasConceptScore W2912981918C171606756 @default.
- W2912981918 hasConceptScore W2912981918C19875794 @default.
- W2912981918 hasConceptScore W2912981918C33923547 @default.
- W2912981918 hasConceptScore W2912981918C41008148 @default.
- W2912981918 hasFunder F4320320300 @default.
- W2912981918 hasFunder F4320321764 @default.
- W2912981918 hasFunder F4320321837 @default.
- W2912981918 hasFunder F4320321864 @default.
- W2912981918 hasFunder F4320322025 @default.
- W2912981918 hasFunder F4320327970 @default.
- W2912981918 hasFunder F4320334905 @default.
- W2912981918 hasFunder F4320338279 @default.
- W2912981918 hasLocation W29129819181 @default.
- W2912981918 hasOpenAccess W2912981918 @default.
- W2912981918 hasPrimaryLocation W29129819181 @default.
- W2912981918 hasRelatedWork W2572405493 @default.
- W2912981918 hasRelatedWork W2961085424 @default.
- W2912981918 hasRelatedWork W3046775127 @default.
- W2912981918 hasRelatedWork W3107474891 @default.
- W2912981918 hasRelatedWork W3209574120 @default.
- W2912981918 hasRelatedWork W4205958290 @default.
- W2912981918 hasRelatedWork W4286629047 @default.
- W2912981918 hasRelatedWork W4306321456 @default.
- W2912981918 hasRelatedWork W4306674287 @default.
- W2912981918 hasRelatedWork W4224009465 @default.
- W2912981918 hasVolume "271" @default.
- W2912981918 isParatext "false" @default.
- W2912981918 isRetracted "false" @default.
- W2912981918 magId "2912981918" @default.
- W2912981918 workType "article" @default.