FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016970897> ?p ?o ?g. }

• W3016970897 endingPage "673" @default.
• W3016970897 startingPage "665" @default.
• W3016970897 abstract "Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today’s machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this Perspective we seek to distil how many of deep learning’s failures can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in comparative psychology, education and linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications. Deep learning has resulted in impressive achievements, but under what circumstances does it fail, and why? The authors propose that its failures are a consequence of shortcut learning, a common characteristic across biological and artificial systems in which strategies that appear to have solved a problem fail unexpectedly under different circumstances." @default.
• W3016970897 created "2020-04-24" @default.
• W3016970897 creator A5000111344 @default.
• W3016970897 creator A5033598239 @default.
• W3016970897 creator A5043113119 @default.
• W3016970897 creator A5043258699 @default.
• W3016970897 creator A5061457780 @default.
• W3016970897 creator A5076080916 @default.
• W3016970897 creator A5086801305 @default.
• W3016970897 date "2020-11-10" @default.
• W3016970897 modified "2023-10-18" @default.
• W3016970897 title "Shortcut learning in deep neural networks" @default.
• W3016970897 cites W1677182931 @default.
• W3016970897 cites W176780229 @default.
• W3016970897 cites W1932198206 @default.
• W3016970897 cites W1966678693 @default.
• W3016970897 cites W1971099716 @default.
• W3016970897 cites W2024748392 @default.
• W3016970897 cites W2031342017 @default.
• W3016970897 cites W2035209808 @default.
• W3016970897 cites W2036167211 @default.
• W3016970897 cites W2051429471 @default.
• W3016970897 cites W2103163130 @default.
• W3016970897 cites W2117539524 @default.
• W3016970897 cites W2122120648 @default.
• W3016970897 cites W2137983211 @default.
• W3016970897 cites W2151554678 @default.
• W3016970897 cites W2159564241 @default.
• W3016970897 cites W2257979135 @default.
• W3016970897 cites W2282821441 @default.
• W3016970897 cites W2363898149 @default.
• W3016970897 cites W2489332873 @default.
• W3016970897 cites W2553474785 @default.
• W3016970897 cites W2574978968 @default.
• W3016970897 cites W2763549966 @default.
• W3016970897 cites W2786808285 @default.
• W3016970897 cites W2811374795 @default.
• W3016970897 cites W2883386984 @default.
• W3016970897 cites W2889706728 @default.
• W3016970897 cites W2903867357 @default.
• W3016970897 cites W2913323966 @default.
• W3016970897 cites W2946579496 @default.
• W3016970897 cites W2946609015 @default.
• W3016970897 cites W2952984539 @default.
• W3016970897 cites W2962736243 @default.
• W3016970897 cites W2962843521 @default.
• W3016970897 cites W2963305465 @default.
• W3016970897 cites W2963826402 @default.
• W3016970897 cites W2963969878 @default.
• W3016970897 cites W2963995504 @default.
• W3016970897 cites W2964128011 @default.
• W3016970897 cites W2965130685 @default.
• W3016970897 cites W2966556569 @default.
• W3016970897 cites W2968993450 @default.
• W3016970897 cites W2970101294 @default.
• W3016970897 cites W2970946372 @default.
• W3016970897 cites W2975512858 @default.
• W3016970897 cites W2989536561 @default.
• W3016970897 cites W3015475346 @default.
• W3016970897 cites W3018252856 @default.
• W3016970897 cites W3100711616 @default.
• W3016970897 cites W4240726888 @default.
• W3016970897 cites W4300408123 @default.
• W3016970897 cites W4362206490 @default.
• W3016970897 doi "https://doi.org/10.1038/s42256-020-00257-z" @default.
• W3016970897 hasPublicationYear "2020" @default.
• W3016970897 type Work @default.
• W3016970897 sameAs 3016970897 @default.
• W3016970897 citedByCount "500" @default.
• W3016970897 countsByYear W30169708972017 @default.
• W3016970897 countsByYear W30169708972019 @default.
• W3016970897 countsByYear W30169708972020 @default.
• W3016970897 countsByYear W30169708972021 @default.
• W3016970897 countsByYear W30169708972022 @default.
• W3016970897 countsByYear W30169708972023 @default.
• W3016970897 crossrefType "journal-article" @default.
• W3016970897 hasAuthorship W3016970897A5000111344 @default.
• W3016970897 hasAuthorship W3016970897A5033598239 @default.
• W3016970897 hasAuthorship W3016970897A5043113119 @default.
• W3016970897 hasAuthorship W3016970897A5043258699 @default.
• W3016970897 hasAuthorship W3016970897A5061457780 @default.
• W3016970897 hasAuthorship W3016970897A5076080916 @default.
• W3016970897 hasAuthorship W3016970897A5086801305 @default.
• W3016970897 hasBestOaLocation W30169708972 @default.
• W3016970897 hasConcept C104317684 @default.
• W3016970897 hasConcept C108583219 @default.
• W3016970897 hasConcept C119857082 @default.
• W3016970897 hasConcept C12713177 @default.
• W3016970897 hasConcept C140331021 @default.
• W3016970897 hasConcept C144133560 @default.
• W3016970897 hasConcept C154945302 @default.
• W3016970897 hasConcept C162853370 @default.
• W3016970897 hasConcept C185592680 @default.
• W3016970897 hasConcept C2984842247 @default.
• W3016970897 hasConcept C41008148 @default.
• W3016970897 hasConcept C50644808 @default.
• W3016970897 hasConcept C55493867 @default.
• W3016970897 hasConcept C61272859 @default.

• next