Lipschitz Properties for Deep Convolutional Networks

@article{Balan2017LipschitzPF,
  title={Lipschitz Properties for Deep Convolutional Networks},
  author={Radu Balan and Maneesh Kumar Singh and Dongmian Zou},
  journal={CoRR},
  year={2017},
  volume={abs/1701.05217}
}
In this paper we discuss the stability properties of convolutional neural networks. Convolutional neural networks are widely used in machine learning. In classification they are mainly used as feature extractors. Ideally, we expect similar features when the inputs are from the same class. That is, we hope to see a small change in the feature vector with respect to a deformation on the input signal. This can be established mathematically, and the key step is to derive the Lipschitz properties… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 148 times. VIEW TWEETS

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Deep learning, Book in preparation for

Yoshua Bengio Ian Goodfellow, Aaron Courville
2016
View 2 Excerpts

Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 2 Excerpts

Deep convolutional neural networks based on semi-discrete frames

2015 IEEE International Symposium on Information Theory (ISIT) • 2015

Invariant Scattering Convolution Networks.

IEEE transactions on pattern analysis and machine intelligence • 2012
View 3 Excerpts

Long Short-Term Memory

Neural Computation • 1997
View 3 Excerpts

Similar Papers

Loading similar papers…