Matches in DBpedia 2014 for { <http://dbpedia.org/resource/Universal_approximation_theorem> ?p ?o. }
Showing items 1 to 35 of
35
with 100 items per page.
- Universal_approximation_theorem abstract "In the mathematical theory of neural networks, the universal approximation theorem states that a feed-forward network with a single hidden layer containing a finite number of neurons (i.e., a multilayer perceptron), can approximate continuous functions on compact subsets of Rn, under mild assumptions on the activation function. The theorem thus states that simple neural networks can represent a wide variety of interesting functions when given appropriate parameters; it does not touch upon the algorithmic learnability of those parameters.One of the first versions of the theorem was proved by George Cybenko in 1989 for sigmoid activation functions.Kurt Hornik showed in 1991 that it is not the specific choice of the activation function, but rather the multilayer feedforward architecture itself which gives neural networks the potential of being universal approximators. The output units are always assumed to be linear. For notational convenience, only the single output case will be shown. The general case can easily be deduced from the single output case.".
- Universal_approximation_theorem wikiPageID "18543448".
- Universal_approximation_theorem wikiPageRevisionID "598898349".
- Universal_approximation_theorem hasPhotoCollection Universal_approximation_theorem.
- Universal_approximation_theorem subject Category:Information,_knowledge,_and_uncertainty.
- Universal_approximation_theorem subject Category:Network_architecture.
- Universal_approximation_theorem subject Category:Networks.
- Universal_approximation_theorem subject Category:Neural_networks.
- Universal_approximation_theorem subject Category:Theorems_in_discrete_mathematics.
- Universal_approximation_theorem type Abstraction100002137.
- Universal_approximation_theorem type Communication100033020.
- Universal_approximation_theorem type ComputerArchitecture106725249.
- Universal_approximation_theorem type Description106724763.
- Universal_approximation_theorem type Group100031264.
- Universal_approximation_theorem type Message106598915.
- Universal_approximation_theorem type Network108434259.
- Universal_approximation_theorem type Networks.
- Universal_approximation_theorem type NeuralNetwork106725467.
- Universal_approximation_theorem type NeuralNetworks.
- Universal_approximation_theorem type Proposition106750804.
- Universal_approximation_theorem type Specification106725067.
- Universal_approximation_theorem type Statement106722453.
- Universal_approximation_theorem type System108435388.
- Universal_approximation_theorem type Theorem106752293.
- Universal_approximation_theorem type TheoremsInDiscreteMathematics.
- Universal_approximation_theorem comment "In the mathematical theory of neural networks, the universal approximation theorem states that a feed-forward network with a single hidden layer containing a finite number of neurons (i.e., a multilayer perceptron), can approximate continuous functions on compact subsets of Rn, under mild assumptions on the activation function.".
- Universal_approximation_theorem label "Universal approximation theorem".
- Universal_approximation_theorem label "مبرهنة التقريب العام".
- Universal_approximation_theorem sameAs 시벤코_정리.
- Universal_approximation_theorem sameAs m.04f_wtc.
- Universal_approximation_theorem sameAs Q7894110.
- Universal_approximation_theorem sameAs Q7894110.
- Universal_approximation_theorem sameAs Universal_approximation_theorem.
- Universal_approximation_theorem wasDerivedFrom Universal_approximation_theorem?oldid=598898349.
- Universal_approximation_theorem isPrimaryTopicOf Universal_approximation_theorem.