Conference on Mathematical Theory of Deep Neural Networks

Oct 31 - Nov 1,  2019


We are now accepting abstracts for poster presentations. We encourage submissions from researchers from diverse disciplines including, but not limited to:

submissions close June 28, 2019

double-blind review

(1 page + additonal page for references)

  • ​​Statistics
  • Physics
  • Computer science
  • Neuroscience
  • Mathematics
  • Psychology
  • Engineering

Topics may address any area of deep learning research such as:

  • expressivity
  • generalization
  • optimization
  • representations
  • computation
  • theory of network architectures including convolutional, fully connected, recurrent, or other topologies

To complement the wealth of conferences focused on applications, all submissions for DeepMath 2019 must include some theoretical and mechanistic understanding of the underlying properties of neural networks.

Abstracts will not be made public (i.e., no official proceedings), and will be doubly-blind reviewed and selected for quality. All poster submissions should be properly anonymized in order to allow for blind refereeing. Submissions should be no more than 1 page although a second page may be used for references. Authors should submit a pdf file prepared using the  Latex style file available here   and should adopt all formatting, subject headings, font sizes, etc. defined therein. Submissions that fail to meet the format requirements will not be reviewed. The first author listed on the abstract is considered to be the presenting author. Each presenting author may submit only one abstract.

Investigators interested in having their abstracts considered for presentation should submit their abstracts no later than June 28. 

Authors may submit their abstracts at: