English

A Numerical Investigation of the Minimum Width of a Neural Network

Machine Learning 2019-10-31 v1

Abstract

Neural network width and depth are fundamental aspects of network topology. Universal approximation theorems provide that with increasing width or depth, there exists a neural network that approximates a function arbitrarily well. These theorems assume requirements, such as infinite data, that must be discretized in practice. Through numerical experiments, we seek to test the lower bounds established by Hanin in 2017.

Keywords

Cite

@article{arxiv.1910.13817,
  title  = {A Numerical Investigation of the Minimum Width of a Neural Network},
  author = {Ibrohim Nosirov and Jeffrey M. Hokanson},
  journal= {arXiv preprint arXiv:1910.13817},
  year   = {2019}
}

Comments

Draft manuscript to be submitted to SIAM Undergrad Research Online