Intriguing properties of neural networks

Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus

Research output: Contribution to conferencePaperpeer-review

Abstract

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn uninterpretable solutions that could have counter-intuitive properties. In this paper we report two such properties. First, we find that there is no distinction between individual high level units and random linear combinations of high level units, according to various methods of unit analysis. It suggests that it is the space, rather than the individual units, that contains the semantic information in the high layers of neural networks. Second, we find that deep neural networks learn input-output mappings that are fairly discontinuous to a significant extent. We can cause the network to misclassify an image by applying a certain hardly perceptible perturbation, which is found by maximizing the network’s prediction error. In addition, the specific nature of these perturbations is not a random artifact of learning: the same perturbation can cause a different network, that was trained on a different subset of the dataset, to misclassify the same input.

Original languageEnglish (US)
StatePublished - Jan 1 2014
Event2nd International Conference on Learning Representations, ICLR 2014 - Banff, Canada
Duration: Apr 14 2014Apr 16 2014

Conference

Conference2nd International Conference on Learning Representations, ICLR 2014
CountryCanada
CityBanff
Period4/14/144/16/14

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Education
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Intriguing properties of neural networks'. Together they form a unique fingerprint.

Cite this