Evolution of Active Categorical Image Classification via Saccadic Eye Movement

  • Randal S. OlsonEmail author
  • Jason H. Moore
  • Christoph Adami
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9921)


Pattern recognition and classification is a central concern for modern information processing systems. In particular, one key challenge to image and video classification has been that the computational cost of image processing scales linearly with the number of pixels in the image or video. Here we present an intelligent machine (the “active categorical classifier,” or ACC) that is inspired by the saccadic movements of the eye, and is capable of classifying images by selectively scanning only a portion of the image. We harness evolutionary computation to optimize the ACC on the MNIST hand-written digit classification task, and provide a proof-of-concept that the ACC works on noisy multi-class data. We further analyze the ACC and demonstrate its ability to classify images after viewing only a fraction of the pixels, and provide insight on future research paths to further improve upon the ACC presented here.


Active categorical perception Attention-based processing Evolutionary computation Machine learning Supervised classification 



We thank David B. Knoester, Arend Hintze, and Jeff Clune for their valuable input during the development of this project. We also thank the Michigan State University High Performance Computing Center for the use of their computing resources. This work was supported in part by the National Science Foundation BEACON Center under Cooperative Agreement DBI-0939454, and in part by National Institutes of Health grants LM009012, LM010098, and EY022300.


  1. 1.
    Trier, O.D., Jain, A.K., Taxt, T.: Feature extraction methods for character recognition - a survey. Pattern Recogn. 29, 641–662 (1999)CrossRefGoogle Scholar
  2. 2.
    LeCun, Y., Boser, B., Denker, J.S., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541–551 (1989)CrossRefGoogle Scholar
  3. 3.
    Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, NIPS 2009, pp. 2204–2212 (2014)Google Scholar
  4. 4.
    Itti, L., Koch, C.: Computational modelling of visual attention. Nat. Rev. Neurosci. 2, 194–203 (2001)CrossRefGoogle Scholar
  5. 5.
    Edlund, J., Chaumont, N., Hintze, A., et al.: Integrated information increases with fitness in the evolution of animats. PLoS Comput. Biol. 7, e1002236 (2011)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Olson, R., Hintze, A., Dyer, F., Knoester, D., Adami, C.: Predator confusion is sufficient to evolve swarming behaviour. J. Roy. Soc. Interface 10, 20130305 (2013)CrossRefGoogle Scholar
  7. 7.
    Chapman, S., Knoester, D., Hintze, A., Adami, C.: Evolution of an artificial visual cortex for image recognition. In: Liò, P., et al. (eds.) Advances in Artificial Life (ECAL 2013), pp. 1067–1074. MIT Press, Cambridge (2013)CrossRefGoogle Scholar
  8. 8.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  9. 9.
    Marstaller, L., Hintze, A., Adami, C.: Cognitive systems evolve complex representations for adaptive behavior. Neural Comput. 25, 2079–2105 (2013)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Eiben, A., Smith, J.: Introduction to Evolutionary Computing. Springer, Berlin (2003)CrossRefzbMATHGoogle Scholar
  11. 11.
    Olson, R.S., Knoester, D.B., Adami, C.: Evolution of swarming behavior is shaped by how predators attack. Artif. Life 22 (2016)Google Scholar
  12. 12.
    Breiman, L., Cutler, A.: Random forests - classification description, March 2016.
  13. 13.
    Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  14. 14.
    Wan, L., Zeiler, M., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using DropConnect. In: Proceedings of the 30th International Conference on Machine Learning, ICML 2013 (2013)Google Scholar
  15. 15.
    Beer, R.D.: The dynamics of active categorical perception in an evolved model agent. Adapt. Behav. 11, 209–243 (2003)CrossRefGoogle Scholar
  16. 16.
    Nguyen, A., Yosinski, J., Clune, J.: Neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Computer Vision and Pattern Recognition (CVPR 2015). IEEE Press (2015)Google Scholar
  17. 17.
    Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015).
  18. 18.
    Szegedy, C., Zaremba, W., Sutskever, I., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (2014).

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Randal S. Olson
    • 1
    Email author
  • Jason H. Moore
    • 1
  • Christoph Adami
    • 2
  1. 1.Institute for Biomedical InformaticsUniversity of PennsylvaniaPhiladelphiaUSA
  2. 2.Department of Microbiology and Molecular GeneticsMichigan State UniversityEast LansingUSA

Personalised recommendations