Why does deep and cheap learning work so well?

@article{Lin2016WhyDD,
  title={Why does deep and cheap learning work so well?},
  author={Henry W. Lin and Max Tegmark},
  journal={CoRR},
  year={2016},
  volume={abs/1608.08225}
}
We show how the success of deep learning could depend not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can approximate arbitrary functions well, the class of functions of practical interest can frequently be approximated through “cheap learning” with exponentially fewer parameters than generic ones. We explore how properties frequently encountered in physics such as symmetry, locality, compositionality, and polynomial log… CONTINUE READING
Highly Cited
This paper has 172 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 2 times over the past 90 days. VIEW TWEETS

4 Figures & Tables

Topics

Statistics

050100201620172018
Citations per Year

173 Citations

Semantic Scholar estimates that this publication has 173 citations based on the available data.

See our FAQ for additional information.