On the stability of deep networks

Raja Giryes; Guillermo Sapiro; Alex M. Bronstein

On the stability of deep networks

Raja Giryes, Guillermo Sapiro, Alex M. Bronstein

Research output: Contribution to conference › Paper › peer-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 language	English
State	Published - 2015
Externally published	Yes
Event	3rd International Conference on Learning Representations, ICLR 2015 - San Diego, United States Duration: 7 May 2015 → 9 May 2015

Conference

Conference	3rd International Conference on Learning Representations, ICLR 2015
Country/Territory	United States
City	San Diego
Period	7/05/15 → 9/05/15

All Science Journal Classification (ASJC) codes

Education
Linguistics and Language
Language and Linguistics
Computer Science Applications

Cite this

@conference{723bb2ed368f43e9ab0afd8f0954cc9e,

title = "On the stability of deep networks",

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{\textquoteright} 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.",

author = "Raja Giryes and Guillermo Sapiro and Bronstein, {Alex M.}",

note = "Publisher Copyright: {\textcopyright} 2015 International Conference on Learning Representations, ICLR. All rights reserved.; 3rd International Conference on Learning Representations, ICLR 2015 ; Conference date: 07-05-2015 Through 09-05-2015",

year = "2015",

language = "الإنجليزيّة",

}

TY - CONF

T1 - On the stability of deep networks

AU - Giryes, Raja

AU - Sapiro, Guillermo

AU - Bronstein, Alex M.

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85083949952&partnerID=8YFLogxK

M3 - محاضرة

T2 - 3rd International Conference on Learning Representations, ICLR 2015

Y2 - 7 May 2015 through 9 May 2015

ER -

On the stability of deep networks

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Cite this