English

Geometrization of deep networks for the interpretability of deep learning systems

Machine Learning 2019-01-15 v2 Artificial Intelligence Machine Learning

Abstract

How to understand deep learning systems remains an open problem. In this paper we propose that the answer may lie in the geometrization of deep networks. Geometrization is a bridge to connect physics, geometry, deep network and quantum computation and this may result in a new scheme to reveal the rule of the physical world. By comparing the geometry of image matching and deep networks, we show that geometrization of deep networks can be used to understand existing deep learning systems and it may also help to solve the interpretability problem of deep learning systems.

Keywords

Cite

@article{arxiv.1901.02354,
  title  = {Geometrization of deep networks for the interpretability of deep learning systems},
  author = {Xiao Dong and Ling Zhou},
  journal= {arXiv preprint arXiv:1901.02354},
  year   = {2019}
}

Comments

9 pages, draft version