Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224930237> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4224930237 abstract "Stochastic gradient descent (SGD) is a premium optimization method for training neural networks, especially for learning objectively defined labels such as image objects and events. When a neural network is instead faced with subjectively defined labels--such as human demonstrations or annotations--SGD may struggle to explore the deceptive and noisy loss landscapes caused by the inherent bias and subjectivity of humans. While neural networks are often trained via preference learning algorithms in an effort to eliminate such data noise, the de facto training methods rely on gradient descent. Motivated by the lack of empirical studies on the impact of evolutionary search to the training of preference learners, we introduce the RankNEAT algorithm which learns to rank through neuroevolution of augmenting topologies. We test the hypothesis that RankNEAT outperforms traditional gradient-based preference learning within the affective computing domain, in particular predicting annotated player arousal from the game footage of three dissimilar games. RankNEAT yields superior performances compared to the gradient-based preference learner (RankNet) in the majority of experiments since its architecture optimization capacity acts as an efficient feature selection mechanism, thereby, eliminating overfitting. Results suggest that RankNEAT is a viable and highly efficient evolutionary alternative to preference learning." @default.
- W4224930237 created "2022-04-28" @default.
- W4224930237 creator A5012075090 @default.
- W4224930237 creator A5043198300 @default.
- W4224930237 creator A5056006892 @default.
- W4224930237 creator A5057445534 @default.
- W4224930237 date "2022-07-08" @default.
- W4224930237 modified "2023-10-18" @default.
- W4224930237 title "RankNEAT" @default.
- W4224930237 cites W1576434095 @default.
- W4224930237 cites W1801780804 @default.
- W4224930237 cites W1935515061 @default.
- W4224930237 cites W1964166287 @default.
- W4224930237 cites W1980480036 @default.
- W4224930237 cites W1981950962 @default.
- W4224930237 cites W1999380910 @default.
- W4224930237 cites W2039082187 @default.
- W4224930237 cites W2056364562 @default.
- W4224930237 cites W2103184652 @default.
- W4224930237 cites W2108598243 @default.
- W4224930237 cites W2113410615 @default.
- W4224930237 cites W2117847384 @default.
- W4224930237 cites W2134514463 @default.
- W4224930237 cites W2137699621 @default.
- W4224930237 cites W2138776737 @default.
- W4224930237 cites W2143331230 @default.
- W4224930237 cites W2166834249 @default.
- W4224930237 cites W2253728219 @default.
- W4224930237 cites W2479609865 @default.
- W4224930237 cites W2787552263 @default.
- W4224930237 cites W2787876196 @default.
- W4224930237 cites W2888451463 @default.
- W4224930237 cites W2898353388 @default.
- W4224930237 cites W2900358852 @default.
- W4224930237 cites W3046768359 @default.
- W4224930237 cites W3098851962 @default.
- W4224930237 cites W3202107015 @default.
- W4224930237 doi "https://doi.org/10.1145/3512290.3528744" @default.
- W4224930237 hasPublicationYear "2022" @default.
- W4224930237 type Work @default.
- W4224930237 citedByCount "1" @default.
- W4224930237 crossrefType "proceedings-article" @default.
- W4224930237 hasAuthorship W4224930237A5012075090 @default.
- W4224930237 hasAuthorship W4224930237A5043198300 @default.
- W4224930237 hasAuthorship W4224930237A5056006892 @default.
- W4224930237 hasAuthorship W4224930237A5057445534 @default.
- W4224930237 hasBestOaLocation W42249302372 @default.
- W4224930237 hasConcept C105795698 @default.
- W4224930237 hasConcept C118070581 @default.
- W4224930237 hasConcept C119857082 @default.
- W4224930237 hasConcept C154945302 @default.
- W4224930237 hasConcept C206688291 @default.
- W4224930237 hasConcept C22019652 @default.
- W4224930237 hasConcept C2781249084 @default.
- W4224930237 hasConcept C33923547 @default.
- W4224930237 hasConcept C41008148 @default.
- W4224930237 hasConcept C50644808 @default.
- W4224930237 hasConceptScore W4224930237C105795698 @default.
- W4224930237 hasConceptScore W4224930237C118070581 @default.
- W4224930237 hasConceptScore W4224930237C119857082 @default.
- W4224930237 hasConceptScore W4224930237C154945302 @default.
- W4224930237 hasConceptScore W4224930237C206688291 @default.
- W4224930237 hasConceptScore W4224930237C22019652 @default.
- W4224930237 hasConceptScore W4224930237C2781249084 @default.
- W4224930237 hasConceptScore W4224930237C33923547 @default.
- W4224930237 hasConceptScore W4224930237C41008148 @default.
- W4224930237 hasConceptScore W4224930237C50644808 @default.
- W4224930237 hasLocation W42249302371 @default.
- W4224930237 hasLocation W42249302372 @default.
- W4224930237 hasLocation W42249302373 @default.
- W4224930237 hasOpenAccess W4224930237 @default.
- W4224930237 hasPrimaryLocation W42249302371 @default.
- W4224930237 hasRelatedWork W1996541855 @default.
- W4224930237 hasRelatedWork W2940336242 @default.
- W4224930237 hasRelatedWork W2985459377 @default.
- W4224930237 hasRelatedWork W2989932438 @default.
- W4224930237 hasRelatedWork W3011996705 @default.
- W4224930237 hasRelatedWork W3099765033 @default.
- W4224930237 hasRelatedWork W3128220493 @default.
- W4224930237 hasRelatedWork W3175189414 @default.
- W4224930237 hasRelatedWork W4210794429 @default.
- W4224930237 hasRelatedWork W4224929651 @default.
- W4224930237 isParatext "false" @default.
- W4224930237 isRetracted "false" @default.
- W4224930237 workType "article" @default.