An Interactive Node-Link Visualization of Convolutional Neural Networks

@inproceedings{Harley2015AnIN,
  title={An Interactive Node-Link Visualization of Convolutional Neural Networks},
  author={Adam W. Harley},
  booktitle={ISVC},
  year={2015}
}
Convolutional neural networks are at the core of state-ofthe-art approaches to a variety of computer vision tasks. Visualizations of neural networks typically take the form of static diagrams, or interactive toy-sized networks, which fail to illustrate the networks’ scale and complexity, and furthermore do not enable meaningful experimentation. Motivated by this observation, this paper presents a new interactive visualization of neural networks trained on handwritten digit recognition, with the… CONTINUE READING
Highly Cited
This paper has 39 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 22 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 30 references

Neural Java: Neural networks tutorial with Java applets

  • F. D. Corbett, H. C. Card
  • http://lcn.epfl.ch/tutorial/english/. Accessed on
  • 2000
Highly Influential
5 Excerpts

ConvNetJS: Deep learning in your browser

  • A. Karpathy
  • http://cs. stanford.edu/people/karpathy/convnetjs…
  • 2014
2 Excerpts

Similar Papers

Loading similar papers…