Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034795257> ?p ?o ?g. }
- W3034795257 abstract "We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks. Instead of using backpropagation to learn features, GLNs have a distributed and local credit assignment mechanism based on optimizing a convex objective. This gives rise to many desirable properties including universality, data-efficient online learning, trivial interpretability and robustness to catastrophic forgetting. We extend the GLN framework from classification to multiple regression and density modelling by generalizing geometric mixing to a product of Gaussian densities. The G-GLN achieves competitive or state-of-the-art performance on several univariate and multivariate regression benchmarks, and we demonstrate its applicability to practical tasks including online contextual bandits and density estimation via denoising." @default.
- W3034795257 created "2020-06-19" @default.
- W3034795257 creator A5003238807 @default.
- W3034795257 creator A5013028446 @default.
- W3034795257 creator A5017031238 @default.
- W3034795257 creator A5033557144 @default.
- W3034795257 creator A5060709021 @default.
- W3034795257 creator A5088896420 @default.
- W3034795257 date "2020-06-10" @default.
- W3034795257 modified "2023-09-27" @default.
- W3034795257 title "Gaussian Gated Linear Networks" @default.
- W3034795257 cites W1505878979 @default.
- W3034795257 cites W1506806321 @default.
- W3034795257 cites W1510444525 @default.
- W3034795257 cites W1719489212 @default.
- W3034795257 cites W2012833704 @default.
- W3034795257 cites W2013035813 @default.
- W3034795257 cites W2077052576 @default.
- W3034795257 cites W2089217417 @default.
- W3034795257 cites W2099231026 @default.
- W3034795257 cites W2108677974 @default.
- W3034795257 cites W2120340025 @default.
- W3034795257 cites W2124914669 @default.
- W3034795257 cites W2129069237 @default.
- W3034795257 cites W2148825261 @default.
- W3034795257 cites W2149764047 @default.
- W3034795257 cites W2157992637 @default.
- W3034795257 cites W2168405694 @default.
- W3034795257 cites W2271840356 @default.
- W3034795257 cites W2296319761 @default.
- W3034795257 cites W241901432 @default.
- W3034795257 cites W2513180554 @default.
- W3034795257 cites W2614634292 @default.
- W3034795257 cites W2622604310 @default.
- W3034795257 cites W2771657877 @default.
- W3034795257 cites W2783494467 @default.
- W3034795257 cites W2911586496 @default.
- W3034795257 cites W2946054758 @default.
- W3034795257 cites W2946894912 @default.
- W3034795257 cites W2949536823 @default.
- W3034795257 cites W2952502547 @default.
- W3034795257 cites W2963580001 @default.
- W3034795257 cites W2963921132 @default.
- W3034795257 cites W2964319207 @default.
- W3034795257 cites W2964330179 @default.
- W3034795257 cites W2969724595 @default.
- W3034795257 cites W2971246930 @default.
- W3034795257 cites W2990583358 @default.
- W3034795257 cites W2995029131 @default.
- W3034795257 cites W2997570648 @default.
- W3034795257 cites W3004619082 @default.
- W3034795257 cites W3006992011 @default.
- W3034795257 cites W3174224867 @default.
- W3034795257 cites W582134693 @default.
- W3034795257 cites W830076066 @default.
- W3034795257 hasPublicationYear "2020" @default.
- W3034795257 type Work @default.
- W3034795257 sameAs 3034795257 @default.
- W3034795257 citedByCount "0" @default.
- W3034795257 crossrefType "posted-content" @default.
- W3034795257 hasAuthorship W3034795257A5003238807 @default.
- W3034795257 hasAuthorship W3034795257A5013028446 @default.
- W3034795257 hasAuthorship W3034795257A5017031238 @default.
- W3034795257 hasAuthorship W3034795257A5033557144 @default.
- W3034795257 hasAuthorship W3034795257A5060709021 @default.
- W3034795257 hasAuthorship W3034795257A5088896420 @default.
- W3034795257 hasConcept C104317684 @default.
- W3034795257 hasConcept C105795698 @default.
- W3034795257 hasConcept C11413529 @default.
- W3034795257 hasConcept C119857082 @default.
- W3034795257 hasConcept C121332964 @default.
- W3034795257 hasConcept C124101348 @default.
- W3034795257 hasConcept C138885662 @default.
- W3034795257 hasConcept C153180895 @default.
- W3034795257 hasConcept C154945302 @default.
- W3034795257 hasConcept C155032097 @default.
- W3034795257 hasConcept C161584116 @default.
- W3034795257 hasConcept C163716315 @default.
- W3034795257 hasConcept C185592680 @default.
- W3034795257 hasConcept C199163554 @default.
- W3034795257 hasConcept C2781067378 @default.
- W3034795257 hasConcept C33923547 @default.
- W3034795257 hasConcept C41008148 @default.
- W3034795257 hasConcept C41895202 @default.
- W3034795257 hasConcept C48921125 @default.
- W3034795257 hasConcept C50644808 @default.
- W3034795257 hasConcept C55493867 @default.
- W3034795257 hasConcept C62520636 @default.
- W3034795257 hasConcept C63479239 @default.
- W3034795257 hasConcept C7149132 @default.
- W3034795257 hasConcept C83546350 @default.
- W3034795257 hasConceptScore W3034795257C104317684 @default.
- W3034795257 hasConceptScore W3034795257C105795698 @default.
- W3034795257 hasConceptScore W3034795257C11413529 @default.
- W3034795257 hasConceptScore W3034795257C119857082 @default.
- W3034795257 hasConceptScore W3034795257C121332964 @default.
- W3034795257 hasConceptScore W3034795257C124101348 @default.
- W3034795257 hasConceptScore W3034795257C138885662 @default.
- W3034795257 hasConceptScore W3034795257C153180895 @default.
- W3034795257 hasConceptScore W3034795257C154945302 @default.