FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034931424> ?p ?o ?g. }

• W3034931424 abstract "Due to recent debate over the biological plausibility of backpropagation (BP), finding an alternative network optimization strategy has become an active area of interest. We design a new type of kernel network, that is solved greedily, to theoretically answer several questions of interest. First, if BP is difficult to simulate in the brain, are there instead network weights (requiring minimum computation) that allow a greedily trained network to classify any pattern. Perhaps a simple repetition of some basic rule can yield a network equally powerful as ones trained by BP with Stochastic Gradient Descent (SGD). Second, can a greedily trained network converge to a kernel? What kernel will it converge to? Third, is this trivial solution optimal? How is the optimal solution related to generalization? Lastly, can we theoretically identify the network width and depth without a grid search? We prove that the kernel embedding is the trivial solution that compels the greedy procedure to converge to a kernel with Universal property. Yet, this trivial solution is not even optimal. By obtaining the optimal solution spectrally, it provides insight into the generalization of the network while informing us of the network width and depth." @default.
• W3034931424 created "2020-06-19" @default.
• W3034931424 creator A5004160420 @default.
• W3034931424 creator A5011474053 @default.
• W3034931424 creator A5042038501 @default.
• W3034931424 creator A5073729816 @default.
• W3034931424 date "2020-06-15" @default.
• W3034931424 modified "2023-09-27" @default.
• W3034931424 title "Layer-wise Learning of Kernel Dependence Networks" @default.
• W3034931424 cites W1493372406 @default.
• W3034931424 cites W1589901016 @default.
• W3034931424 cites W1638081485 @default.
• W3034931424 cites W1677182931 @default.
• W3034931424 cites W1777649940 @default.
• W3034931424 cites W1920328734 @default.
• W3034931424 cites W1988115241 @default.
• W3034931424 cites W2001619934 @default.
• W3034931424 cites W2003357516 @default.
• W3034931424 cites W2097308346 @default.
• W3034931424 cites W2103496339 @default.
• W3034931424 cites W2129476886 @default.
• W3034931424 cites W2137055149 @default.
• W3034931424 cites W2144902422 @default.
• W3034931424 cites W2159110831 @default.
• W3034931424 cites W2161388792 @default.
• W3034931424 cites W2529004582 @default.
• W3034931424 cites W2578935686 @default.
• W3034931424 cites W2604086949 @default.
• W3034931424 cites W2766678531 @default.
• W3034931424 cites W2785626633 @default.
• W3034931424 cites W2799135322 @default.
• W3034931424 cites W2809090039 @default.
• W3034931424 cites W2899771611 @default.
• W3034931424 cites W2913473169 @default.
• W3034931424 cites W2913907987 @default.
• W3034931424 cites W2917668703 @default.
• W3034931424 cites W2962698288 @default.
• W3034931424 cites W2963096987 @default.
• W3034931424 cites W2963097630 @default.
• W3034931424 cites W2963100491 @default.
• W3034931424 cites W2963440770 @default.
• W3034931424 cites W2963477238 @default.
• W3034931424 cites W2963626582 @default.
• W3034931424 cites W2963809228 @default.
• W3034931424 cites W2964088238 @default.
• W3034931424 cites W2964122761 @default.
• W3034931424 cites W2969343193 @default.
• W3034931424 cites W2970249264 @default.
• W3034931424 cites W2970330753 @default.
• W3034931424 cites W2970332347 @default.
• W3034931424 cites W2970454961 @default.
• W3034931424 cites W2970795117 @default.
• W3034931424 cites W2970935073 @default.
• W3034931424 cites W2971043187 @default.
• W3034931424 cites W3007253500 @default.
• W3034931424 cites W3016391357 @default.
• W3034931424 cites W3101183984 @default.
• W3034931424 cites W3137695714 @default.
• W3034931424 cites W3005347330 @default.
• W3034931424 hasPublicationYear "2020" @default.
• W3034931424 type Work @default.
• W3034931424 sameAs 3034931424 @default.
• W3034931424 citedByCount "0" @default.
• W3034931424 crossrefType "posted-content" @default.
• W3034931424 hasAuthorship W3034931424A5004160420 @default.
• W3034931424 hasAuthorship W3034931424A5011474053 @default.
• W3034931424 hasAuthorship W3034931424A5042038501 @default.
• W3034931424 hasAuthorship W3034931424A5073729816 @default.
• W3034931424 hasConcept C111472728 @default.
• W3034931424 hasConcept C11413529 @default.
• W3034931424 hasConcept C118615104 @default.
• W3034931424 hasConcept C122280245 @default.
• W3034931424 hasConcept C12267149 @default.
• W3034931424 hasConcept C126255220 @default.
• W3034931424 hasConcept C134306372 @default.
• W3034931424 hasConcept C138885662 @default.
• W3034931424 hasConcept C154945302 @default.
• W3034931424 hasConcept C155032097 @default.
• W3034931424 hasConcept C177148314 @default.
• W3034931424 hasConcept C2780586882 @default.
• W3034931424 hasConcept C33923547 @default.
• W3034931424 hasConcept C41008148 @default.
• W3034931424 hasConcept C50644808 @default.
• W3034931424 hasConcept C74193536 @default.
• W3034931424 hasConceptScore W3034931424C111472728 @default.
• W3034931424 hasConceptScore W3034931424C11413529 @default.
• W3034931424 hasConceptScore W3034931424C118615104 @default.
• W3034931424 hasConceptScore W3034931424C122280245 @default.
• W3034931424 hasConceptScore W3034931424C12267149 @default.
• W3034931424 hasConceptScore W3034931424C126255220 @default.
• W3034931424 hasConceptScore W3034931424C134306372 @default.
• W3034931424 hasConceptScore W3034931424C138885662 @default.
• W3034931424 hasConceptScore W3034931424C154945302 @default.
• W3034931424 hasConceptScore W3034931424C155032097 @default.
• W3034931424 hasConceptScore W3034931424C177148314 @default.
• W3034931424 hasConceptScore W3034931424C2780586882 @default.
• W3034931424 hasConceptScore W3034931424C33923547 @default.
• W3034931424 hasConceptScore W3034931424C41008148 @default.
• W3034931424 hasConceptScore W3034931424C50644808 @default.
• W3034931424 hasConceptScore W3034931424C74193536 @default.

• next