On the stability of deep networks

Raja Giryes, Guillermo Sapiro, Alex M. Bronstein

Research output: Contribution to conferencePaperpeer-review

Abstract

In this work we study the properties of deep neural networks (DNN) 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. A longer version of this paper with more results and details can be found in (Giryes et al., 2015). In particular, we formally prove in (Giryes et al., 2015) that DNN with random Gaussian weights perform a distance-preserving embedding of the data, with a special treatment for in-class and out-of-class data.

Original languageEnglish
StatePublished - 2015
Externally publishedYes
Event3rd International Conference on Learning Representations, ICLR 2015 - San Diego, United States
Duration: 7 May 20159 May 2015

Conference

Conference3rd International Conference on Learning Representations, ICLR 2015
Country/TerritoryUnited States
CitySan Diego
Period7/05/159/05/15

Fingerprint

Dive into the research topics of 'On the stability of deep networks'. Together they form a unique fingerprint.

Cite this