ON RANDOM DEEP AUTOENCODERS: EXACT ASYMP-

@inproceedings{2018ONRD,
  title={ON RANDOM DEEP AUTOENCODERS: EXACT ASYMP-},
  author={},
  year={2018}
}
  • Published 2018
We study the behavior of weight-tied multilayer vanilla autoencoders under the assumption of random weights. Via an exact characterization in the limit of large dimensions, our analysis reveals interesting phase transition phenomena when the depth becomes large. This, in particular, provides quantitative answers and insights to three questions that were yet fully understood in the literature. Firstly, we provide a precise answer on how the random deep weight-tied autoencoder model performs… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 59 REFERENCES

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

A mean field view of the landscape of two-layer neural networks

  • Proceedings of the National Academy of Sciences of the United States of America
  • 2018
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL