Convolutional Neural Networks Analyzed via Convolutional Sparse Coding

@article{Papyan2017ConvolutionalNN,
  title={Convolutional Neural Networks Analyzed via Convolutional Sparse Coding},
  author={Vardan Papyan and Yaniv Romano and Michael Elad},
  journal={Journal of Machine Learning Research},
  year={2017},
  volume={18},
  pages={83:1-83:52}
}
 The relation between CNN and the sparse-land model has been defined via our multi-layer convolutional sparse coding model  We have shown that the forward pass of CNN is in fact a pursuit algorithm that aims to decompose the signals belonging to our model into their building blocks  Leveraging this connection, we were able to attribute to the CNN architecture theoretical claims such as uniqueness of the representations (feature maps) throughout the network and their stable estimation, all… CONTINUE READING
Highly Cited
This paper has 88 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 22 times over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.

88 Citations

05020172018
Citations per Year
Semantic Scholar estimates that this publication has 88 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 51 references

Similar Papers

Loading similar papers…