arXiv:1412.5896 Abstract | arXiv Analytics

arXiv:1412.5896 [stat.ML]Abstract References Reviews Resources

On the Stability of Deep Networks

Raja Giryes, Guillermo Sapiro, Alex M. Bronstein

Published 2014-12-18Version 1

In this work we study the properties of deep neural networks with random weights. We formally prove that these networks perform a distance-preserving embedding of the data. Based on this we then draw conclusions on the size of the training data and the networks' structure.

Comments: 3 pages

Categories: stat.ML, cs.IT, cs.LG, cs.NE, math.IT, math.MG

Keywords: deep networks, deep neural networks, draw conclusions, random weights, networks perform

Related articles: Most relevant | Search more

arXiv:2205.10217 [stat.ML] (Published 2022-05-20)

Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization

Simone Bombari, Mohammad Hossein Amani, Marco Mondelli

arXiv:1712.09482 [stat.ML] (Published 2017-12-27)

Robust Loss Functions under Label Noise for Deep Neural Networks

Aritra Ghosh, Himanshu Kumar, P. S. Sastry

arXiv:1806.01316 [stat.ML] (Published 2018-06-04)

Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach