Analytic function approximation by path-norm-regularized deep neural networks

HIGHLIGHTS

• who: Aleksandr Beknazaryan from the Institute of Environmental and Agricultural Biology (X-BIO), University of Tyumen, Volodarskogo , have published the research work: Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks, in the Journal: Entropy 2022, 24, 1136. of /2022/
• what: The authors show that neural networks with an absolute value activation function and with network path norm network sizes and network weights having logarithmic dependence on 1/u03b5 can u03b5-approximate functions that are analytic on certain regions of Cd. The aim of this paper is the construction of path-norm-regularized networks . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.