Intriguing properties of neural networks

  title={Intriguing properties of neural networks},
  author={Christian Szegedy and Wojciech Zaremba and Ilya Sutskever and Joan Bruna and Dumitru Erhan and Ian J. Goodfellow and Rob Fergus},
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… CONTINUE READING
Highly Influential
This paper has highly influenced 266 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 1,986 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications citing this paper.

1,986 Citations

Citations per Year
Semantic Scholar estimates that this publication has 1,986 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 15 references

Learning deep architectures for ai

  • Yoshua Bengio
  • Foundations and trends® in Machine Learning,
  • 2009
1 Excerpt

Similar Papers

Loading similar papers…