Intriguing properties of neural networks

@article{Szegedy2014IntriguingPO,
  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},
  journal={CoRR},
  year={2014},
  volume={abs/1312.6199}
}
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

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 1,661 CITATIONS, ESTIMATED 39% COVERAGE

FILTER CITATIONS BY YEAR

2014
2019

CITATION STATISTICS

  • 341 Highly Influenced Citations

  • Averaged 437 Citations per year over the last 3 years

  • 52% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES

Learning deep architectures for ai

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

Similar Papers

Loading similar papers…