06/12/2020

Rational neural networks

Nicolas Boulle, Yuji Nakatsukasa, Alex J Townsend

Keywords:

Abstract Paper Similar Papers

Abstract: We consider neural networks with rational activation functions. The choice of the nonlinear activation function in deep learning architectures is crucial and heavily impacts the performance of a neural network. We establish optimal bounds in terms of network complexity and prove that rational neural networks approximate smooth functions more efficiently than ReLU networks with exponentially smaller depth. The flexibility and smoothness of rational activation functions make them an attractive alternative to ReLU, as we demonstrate with numerical experiments.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at NeurIPS 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 9:24 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 10:02 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 4:34 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 14:28 
 0
 0
 0
 0
 20:00 
 0
 0
 0
 0
 14:09 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 8:56 
 0
 0
 0
 0
 14:46 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 9:51 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 13:29 
 0
 0
 0
 0
 13:48 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 11:15 
 0
 0
 0
 0
 14:52 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 16:47 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 3:17