Skip to main content
1 of 2
Skander H.
  • 12.1k
  • 2
  • 44
  • 99

Does the universal approximation theorem for neural networks hold for any activation function?

Does the universal approximation theorem for neural networks hold for any activation function (sigmoid, ReLU, Softmax, etc...) or is it limited to sigmoid functions?

Skander H.
  • 12.1k
  • 2
  • 44
  • 99