Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete


Apr 04, 2022
Daniel Bertschinger, Christoph Hertrich, Paul Jungeblut, Tillmann Miltzow, Simon Weber

Add code

* 38 pages, 18 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Lower Bounds on the Depth of ReLU Neural Networks


May 31, 2021
Christoph Hertrich, Amitabh Basu, Marco Di Summa, Martin Skutella

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality


May 31, 2021
Vincent Froese, Christoph Hertrich, Rolf Niedermeier

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ReLU Neural Networks for Exact Maximum Flow Computation


Feb 12, 2021
Christoph Hertrich, Leon Sering

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size


May 28, 2020
Christoph Hertrich, Martin Skutella

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email