Approximation of functions from korobov spaces by deep convolutional neural networks

HIGHLIGHTS

• who: Tong Mao from the School of Data Science, City University of Hong Kong, Kowloon, Hong Kong have published the paper: Approximation of functions from Korobov spaces by deep convolutional neural networks, in the Journal: (JOURNAL)
• what: The aim of this paper is to show that DCNNs perform excellently for approximating in Lp (1 u2264 p u2264 u221e) functions from Korobov spaces involving mixed derivatives of order 2. The authors show how to construct the convolutional layers for realizing the approximate products for Q + 1. The authors show how the iterations of tooth functions can . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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