An Interactive Node-Link Visualization of Convolutional Neural Networks

  • Adam W. Harley
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9474)


Convolutional neural networks are at the core of state-of-the-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 intent of showing the actual behavior of the network given user-provided input. The user can interact with the network through a drawing pad, and watch the activation patterns of the network respond in real-time. The visualization is available at


Neural Network Convolutional Neural Network Interactive Visualization Edge Strength Computer Vision Task 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The author gratefully thanks Tim McInerney and Kosta Derpanis for insightful discussions, and for helping improve the manuscript.


  1. 1.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)Google Scholar
  2. 2.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)Google Scholar
  3. 3.
    Corbett, F.D., Card, H.C.: Neural Java: Neural networks tutorial with Java applets (2000). Accessed on 31 Nov 2014
  4. 4.
    Zeiler, Matthew D., Fergus, Rob: Visualizing and understanding convolutional networks. In: Fleet, David, Pajdla, Tomas, Schiele, Bernt, Tuytelaars, Tinne (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 818–833. Springer, Heidelberg (2014) Google Scholar
  5. 5.
    Craven, M.W., Shavlik, J.W.: Visualizing learning and computation in artificial neural networks. Int. J. Artif. Intell. Tools 1, 399–425 (1992)CrossRefGoogle Scholar
  6. 6.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer-Verlag New York Inc, Secaucus, NJ, USA (2006)zbMATHGoogle Scholar
  7. 7.
    Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65, 386–408 (1958)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Lodish, H., Berk, A., Zipursky, S.L., Matsudaira, P., Baltimore, D., Darnell, J.: Molecular Cell Biology, 4th edn. W.H. Freeman, New York (2001) Google Scholar
  9. 9.
    Werbos, P.J.: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Ph.D thesis, Harvard University (1974)Google Scholar
  10. 10.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  11. 11.
    Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: ICCV (2009)Google Scholar
  12. 12.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  13. 13.
    LeCun, Y., Kavukvuoglu, K., Farabet, C.: Convolutional networks and applications in vision. In: ISCAS, pp. 253–256 (2010)Google Scholar
  14. 14.
    Holten, D.: Hierarchical edge bundles: visualization of adjacency relations in hierarchical data. TVCG 12, 741–748 (2006)Google Scholar
  15. 15.
    Al-Awami, A., Beyer, J., Strobelt, H., Kasthuri, N., Lichtman, J., Pfister, H., Hadwiger, M.: NeuroLines: a subway map metaphor for visualizing nanoscale neuronal connectivity. TVCG 20, 2369–2378 (2014)Google Scholar
  16. 16.
    Lex, A., Partl, C., Kalkofen, D., Streit, M., Gratzl, S., Wassermann, A.M., Schmalstieg, D., Pfister, H.: Entourage: visualizing relationships between biological pathways using contextual subsets. TVCG 19, 2536–2545 (2013)Google Scholar
  17. 17.
    Van Ham, F., Perer, A.: Search, show context, expand on demand: supporting large graph exploration with degree-of-interest. TVCG 15, 953–960 (2009)Google Scholar
  18. 18.
    Shneiderman, B.: The eyes have it: a task by data type taxonomy for information visualizations. In: Visual Languages, pp. 336–343 (1996)Google Scholar
  19. 19.
    Zell, A., Mache, N., Hbner, R., Mamier, G., Vogt, M., Schmalzl, M., Herrmann, K.U.: SNNS (Stuttgart Neural Network Simulator). In: Skrzypek, J. (ed.) Neural Network Simulation Environments: The Kluwer International Series in Engineering and Computer Science, vol. 254, pp. 165–186. Springer, US (1994)Google Scholar
  20. 20.
    Streeter, M.J., Ward, M.O., Alvarez, S.A.: N2Vis: an interactive visualization tool for neural networks. In: Visual Data Exploration and Analysis VII, pp. 234–241 (2001)Google Scholar
  21. 21.
    Tzeng, F.Y., Ma, K.L.: Opening the black box - Data driven visualization of neural networks. In: Visualization, pp. 383–390 (2005)Google Scholar
  22. 22.
    Srp, J., Stehlík, L., Suda, M., Šašek, P., Zvánovcová, K.: Interactive neural network simulator (2007). Accessed on 31 Nov 2014
  23. 23.
    Karpathy, A.: ConvNetJS: Deep learning in your browser (2014). Accessed on 31 Nov 2014
  24. 24.
    Henry, N., Fekete, J.D., McGuffin, M.J.: NodeTrix: a hybrid visualization of social networks. TVCG 13, 1302–1309 (2007)Google Scholar
  25. 25.
    Ware, C.: Information Visualization: Perception for Design. Elsevier, Amsterdam (2012) Google Scholar
  26. 26.
    Rogowitz, B.E., Treinish, L.A.: How not to lie with visualization. Comput. Phys. 10, 268–273 (1996)CrossRefGoogle Scholar
  27. 27.
    Nielsen, J.: Usability Engineering. Elsevier, Boston (1993)zbMATHGoogle Scholar
  28. 28.
    Miller, R.B.: Response time in man-computer conversational transactions. In: Proceedings of AFIPS Fall Joint Computer Conference, vol. 33, pp. 267–277 (1968)Google Scholar
  29. 29.
    Card, S.K., Robertson, G.G., Mackinlay, J.D.: The information visualizer: an information workspace. In: ACM CHI, pp. 181–188 (1991)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Computer ScienceRyerson UniversityTorontoCanada

Personalised recommendations