Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387568403> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4387568403 endingPage "100860" @default.
- W4387568403 startingPage "100860" @default.
- W4387568403 abstract "Judging whether an integer can be divided by prime numbers such as 2 or 3 may appear trivial to human beings, but it can be less straightforward for computers. Here, we tested multiple deep learning architectures and feature engineering approaches to classifying integers based on their residues when divided by small prime numbers. We found that the ability of classification critically depends on the feature space. We also evaluated automated machine learning (AutoML) platforms from Amazon, Google, and Microsoft and found that, without appropriately engineered features, they failed on this task. Furthermore, we introduced a method that utilizes linear regression on Fourier series basis vectors and demonstrated its effectiveness. Finally, we evaluated large language models (LLMs) such as GPT-4, GPT-J, LLaMA, and Falcon, and we demonstrated their failures. In conclusion, feature engineering remains an important task to improve performance and increase interpretability of machine learning models, even in the era of AutoML and LLMs." @default.
- W4387568403 created "2023-10-13" @default.
- W4387568403 creator A5016711247 @default.
- W4387568403 creator A5023160828 @default.
- W4387568403 creator A5039395260 @default.
- W4387568403 creator A5053928863 @default.
- W4387568403 date "2023-10-01" @default.
- W4387568403 modified "2023-10-13" @default.
- W4387568403 title "Classification of integers based on residue classes via modern deep learning algorithms" @default.
- W4387568403 cites W2112796928 @default.
- W4387568403 cites W2137983211 @default.
- W4387568403 cites W2151554678 @default.
- W4387568403 cites W2154137718 @default.
- W4387568403 cites W2885195348 @default.
- W4387568403 cites W2944851425 @default.
- W4387568403 cites W2962949934 @default.
- W4387568403 cites W2966284335 @default.
- W4387568403 cites W3140854437 @default.
- W4387568403 cites W3201904098 @default.
- W4387568403 cites W3203309275 @default.
- W4387568403 cites W4213019189 @default.
- W4387568403 cites W4234314512 @default.
- W4387568403 cites W4306955484 @default.
- W4387568403 doi "https://doi.org/10.1016/j.patter.2023.100860" @default.
- W4387568403 hasPublicationYear "2023" @default.
- W4387568403 type Work @default.
- W4387568403 citedByCount "0" @default.
- W4387568403 crossrefType "journal-article" @default.
- W4387568403 hasAuthorship W4387568403A5016711247 @default.
- W4387568403 hasAuthorship W4387568403A5023160828 @default.
- W4387568403 hasAuthorship W4387568403A5039395260 @default.
- W4387568403 hasAuthorship W4387568403A5053928863 @default.
- W4387568403 hasBestOaLocation W43875684031 @default.
- W4387568403 hasConcept C108583219 @default.
- W4387568403 hasConcept C11413529 @default.
- W4387568403 hasConcept C114614502 @default.
- W4387568403 hasConcept C119857082 @default.
- W4387568403 hasConcept C127413603 @default.
- W4387568403 hasConcept C138885662 @default.
- W4387568403 hasConcept C154945302 @default.
- W4387568403 hasConcept C184992742 @default.
- W4387568403 hasConcept C201995342 @default.
- W4387568403 hasConcept C2776401178 @default.
- W4387568403 hasConcept C2778827112 @default.
- W4387568403 hasConcept C2780451532 @default.
- W4387568403 hasConcept C2781067378 @default.
- W4387568403 hasConcept C33923547 @default.
- W4387568403 hasConcept C41008148 @default.
- W4387568403 hasConcept C41895202 @default.
- W4387568403 hasConceptScore W4387568403C108583219 @default.
- W4387568403 hasConceptScore W4387568403C11413529 @default.
- W4387568403 hasConceptScore W4387568403C114614502 @default.
- W4387568403 hasConceptScore W4387568403C119857082 @default.
- W4387568403 hasConceptScore W4387568403C127413603 @default.
- W4387568403 hasConceptScore W4387568403C138885662 @default.
- W4387568403 hasConceptScore W4387568403C154945302 @default.
- W4387568403 hasConceptScore W4387568403C184992742 @default.
- W4387568403 hasConceptScore W4387568403C201995342 @default.
- W4387568403 hasConceptScore W4387568403C2776401178 @default.
- W4387568403 hasConceptScore W4387568403C2778827112 @default.
- W4387568403 hasConceptScore W4387568403C2780451532 @default.
- W4387568403 hasConceptScore W4387568403C2781067378 @default.
- W4387568403 hasConceptScore W4387568403C33923547 @default.
- W4387568403 hasConceptScore W4387568403C41008148 @default.
- W4387568403 hasConceptScore W4387568403C41895202 @default.
- W4387568403 hasLocation W43875684031 @default.
- W4387568403 hasOpenAccess W4387568403 @default.
- W4387568403 hasPrimaryLocation W43875684031 @default.
- W4387568403 hasRelatedWork W2745673637 @default.
- W4387568403 hasRelatedWork W2750075801 @default.
- W4387568403 hasRelatedWork W2905433371 @default.
- W4387568403 hasRelatedWork W3034267371 @default.
- W4387568403 hasRelatedWork W3153597579 @default.
- W4387568403 hasRelatedWork W3164948662 @default.
- W4387568403 hasRelatedWork W3210057995 @default.
- W4387568403 hasRelatedWork W4310278675 @default.
- W4387568403 hasRelatedWork W4361193272 @default.
- W4387568403 hasRelatedWork W4385336128 @default.
- W4387568403 isParatext "false" @default.
- W4387568403 isRetracted "false" @default.
- W4387568403 workType "article" @default.