Computer Science > Neural and Evolutionary Computing
[Submitted on 30 Apr 2015 (v1), last revised 14 Mar 2016 (this version, v5)]
Title:Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
View PDFAbstract:Three important properties of a classification machinery are: (i) the system preserves the core information of the input data; (ii) the training examples convey information about unseen data; and (iii) the system is able to treat differently points from different classes. In this work we show that these fundamental properties are satisfied by the architecture of deep neural networks. We formally prove that these networks with random Gaussian weights perform a distance-preserving embedding of the data, with a special treatment for in-class and out-of-class data. Similar points at the input of the network are likely to have a similar output. The theoretical analysis of deep networks here presented exploits tools used in the compressed sensing and dictionary learning literature, thereby making a formal connection between these important topics. The derived results allow drawing conclusions on the metric learning properties of the network and their relation to its structure, as well as providing bounds on the required size of the training set such that the training examples would represent faithfully the unseen data. The results are validated with state-of-the-art trained networks.
Submission history
From: Raja Giryes [view email][v1] Thu, 30 Apr 2015 16:14:52 UTC (3,098 KB)
[v2] Fri, 1 May 2015 11:30:51 UTC (3,098 KB)
[v3] Wed, 3 Jun 2015 13:53:11 UTC (3,099 KB)
[v4] Mon, 11 Jan 2016 19:25:05 UTC (5,507 KB)
[v5] Mon, 14 Mar 2016 19:17:08 UTC (5,728 KB)
Current browse context:
cs.NE
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
Connected Papers (What is Connected Papers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.