ResNet with one-neuron hidden layers is a Universal Approximator

ResNet with one-neuron hidden layers is a Universal Approximator

We demonstrate that a very deep ResNet with stacked modules that have one neuron per hidden layer and ReLU activation functions can uniformly approximate any Lebesgue integrable function in d dimensions, i.e. ℓ1(Rd). Due to the identity mapping inherent to ResNets, our network has alternating layers...

Full description

Bibliographic Details
Main Authors: Lin, Hongzhou (Author), Jegelka, Stefanie Sabrina (Author)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
Format: Article
Language:English
Published: Morgan Kaufmann Publishers, 2021-01-07T14:35:57Z.
Subjects:
Article
Online Access:Get fulltext

Internet

Get fulltext

Similar Items