The Cybenko theorem is a theorem proved by George Cybenko in 1989 that says that a single hidden layer, feed forward neural network is capable of approximating any continuous, multivariate function to any desired degree of accuracy and that failure to map a function arises from poor choices for <math>\mathbf{w}_1, \mathbf{w}_2, \dots, \mathbf{w}_N, \mathbf{\alpha},</math> and <math>\mathbf{\theta}</math> or an insufficient number of hidden neurons.

PropertyValue
dbpprop:abstract
  • The Cybenko theorem is a theorem proved by George Cybenko in 1989 that says that a single hidden layer, feed forward neural network is capable of approximating any continuous, multivariate function to any desired degree of accuracy and that failure to map a function arises from poor choices for <math>\mathbf{w}_1, \mathbf{w}_2, \dots, \mathbf{w}_N, \mathbf{\alpha},</math> and <math>\mathbf{\theta}</math> or an insufficient number of hidden neurons.
dbpprop:hasPhotoCollection
dbpprop:reference
rdf:type
rdfs:comment
  • The Cybenko theorem is a theorem proved by George Cybenko in 1989 that says that a single hidden layer, feed forward neural network is capable of approximating any continuous, multivariate function to any desired degree of accuracy and that failure to map a function arises from poor choices for <math>\mathbf{w}_1, \mathbf{w}_2, \dots, \mathbf{w}_N, \mathbf{\alpha},</math> and <math>\mathbf{\theta}</math> or an insufficient number of hidden neurons.
rdfs:label
  • Cybenko theorem
owl:sameAs
skos:subject
foaf:page
is dbpprop:redirect of
is owl:sameAs of