FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367187713> ?p ?o ?g. }

• W4367187713 endingPage "126227" @default.
• W4367187713 startingPage "126227" @default.
• W4367187713 abstract "This century saw an unprecedented increase of public and private investments in Artificial Intelligence (AI) and especially in (Deep) Machine Learning (ML). This led to breakthroughs in their practical ability to solve complex real-world problems impacting research and society at large. Instead, our ability to understand the fundamental mechanism behind these breakthroughs has slowed down because of their increased complexity, while in the past breakthroughs often emerged from foundational research. This questioned researchers about the necessity for a new theoretical framework able to help researchers catch up on this lag. One of the still not well understood mechanisms is the so-called over-parametrization, namely the ability of certain models to increase their generalization performance (reduce test error) when the number of parameters is above the interpolating threshold (zero training error). In this paper we will show that this phenomenon can be better understood using both known theories (surveying them in the process) and empirical evidences for both shallow and deep learning algorithms." @default.
• W4367187713 created "2023-04-28" @default.
• W4367187713 creator A5036611143 @default.
• W4367187713 creator A5045802198 @default.
• W4367187713 creator A5072692847 @default.
• W4367187713 date "2023-07-01" @default.
• W4367187713 modified "2023-10-17" @default.
• W4367187713 title "Do we really need a new theory to understand over-parameterization?" @default.
• W4367187713 cites W1507985183 @default.
• W4367187713 cites W1550861865 @default.
• W4367187713 cites W1976354615 @default.
• W4367187713 cites W1976891431 @default.
• W4367187713 cites W1999376700 @default.
• W4367187713 cites W2000119679 @default.
• W4367187713 cites W2009784682 @default.
• W4367187713 cites W2033559768 @default.
• W4367187713 cites W2077366952 @default.
• W4367187713 cites W2082233060 @default.
• W4367187713 cites W2092317945 @default.
• W4367187713 cites W2095165925 @default.
• W4367187713 cites W2112796928 @default.
• W4367187713 cites W2120875792 @default.
• W4367187713 cites W2129538346 @default.
• W4367187713 cites W2146774335 @default.
• W4367187713 cites W2156606213 @default.
• W4367187713 cites W2162152253 @default.
• W4367187713 cites W2162341153 @default.
• W4367187713 cites W2163032969 @default.
• W4367187713 cites W2194775991 @default.
• W4367187713 cites W2473418344 @default.
• W4367187713 cites W2498765815 @default.
• W4367187713 cites W2562742273 @default.
• W4367187713 cites W2566079294 @default.
• W4367187713 cites W2766447205 @default.
• W4367187713 cites W2774873015 @default.
• W4367187713 cites W2790145585 @default.
• W4367187713 cites W2804446681 @default.
• W4367187713 cites W2889399096 @default.
• W4367187713 cites W2902634493 @default.
• W4367187713 cites W2902674365 @default.
• W4367187713 cites W2907047316 @default.
• W4367187713 cites W2911964244 @default.
• W4367187713 cites W2912811302 @default.
• W4367187713 cites W2923764619 @default.
• W4367187713 cites W2944145193 @default.
• W4367187713 cites W2962908518 @default.
• W4367187713 cites W2963094815 @default.
• W4367187713 cites W2963518130 @default.
• W4367187713 cites W2970217468 @default.
• W4367187713 cites W2976306682 @default.
• W4367187713 cites W2979452771 @default.
• W4367187713 cites W2995896684 @default.
• W4367187713 cites W3000508506 @default.
• W4367187713 cites W3005738431 @default.
• W4367187713 cites W3018252856 @default.
• W4367187713 cites W3021058579 @default.
• W4367187713 cites W3043426275 @default.
• W4367187713 cites W3083720136 @default.
• W4367187713 cites W3100743579 @default.
• W4367187713 cites W3101441056 @default.
• W4367187713 cites W3104969455 @default.
• W4367187713 cites W3105622673 @default.
• W4367187713 cites W3111350549 @default.
• W4367187713 cites W3152114226 @default.
• W4367187713 cites W3159210794 @default.
• W4367187713 cites W3161916718 @default.
• W4367187713 cites W3177828909 @default.
• W4367187713 cites W3191067499 @default.
• W4367187713 cites W3197744105 @default.
• W4367187713 cites W4200030970 @default.
• W4367187713 cites W4206410067 @default.
• W4367187713 cites W4213377513 @default.
• W4367187713 cites W4231586238 @default.
• W4367187713 cites W4243551976 @default.
• W4367187713 cites W4247200422 @default.
• W4367187713 cites W4285606245 @default.
• W4367187713 cites W4296935184 @default.
• W4367187713 cites W4297838884 @default.
• W4367187713 doi "https://doi.org/10.1016/j.neucom.2023.126227" @default.
• W4367187713 hasPublicationYear "2023" @default.
• W4367187713 type Work @default.
• W4367187713 citedByCount "0" @default.
• W4367187713 crossrefType "journal-article" @default.
• W4367187713 hasAuthorship W4367187713A5036611143 @default.
• W4367187713 hasAuthorship W4367187713A5045802198 @default.
• W4367187713 hasAuthorship W4367187713A5072692847 @default.
• W4367187713 hasConcept C105795698 @default.
• W4367187713 hasConcept C108583219 @default.
• W4367187713 hasConcept C111472728 @default.
• W4367187713 hasConcept C111919701 @default.
• W4367187713 hasConcept C119857082 @default.
• W4367187713 hasConcept C120936955 @default.
• W4367187713 hasConcept C127413603 @default.
• W4367187713 hasConcept C134306372 @default.
• W4367187713 hasConcept C138885662 @default.
• W4367187713 hasConcept C154945302 @default.
• W4367187713 hasConcept C177148314 @default.
• W4367187713 hasConcept C2780813799 @default.

• next