Deep limits of residual neural networks

HIGHLIGHTS

• who: Matthew Thorpe from the London , DB, UK have published the paper: Deep limits of residual neural networks, in the Journal: (JOURNAL)
• what: Whilst it is known that the residual neural network model is a discretisation of an ordinary differential equation the authors show in a sense. The analysis provides a discrete-to-continuum result for the objective function of the residual neural network training step to a problem constrained by a system of ordinary differential equations; this rigorously connects the discrete setting to a continuum problem. The aim of this paper is to connect . . .
  

   

  

  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.