Advertisement

Adversarial Evolution and Deep Learning – How Does an Artist Play with Our Visual System?

  • Alan BlairEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11453)

Abstract

We create artworks using adversarial coevolution between a genetic program (hercl) generator and a deep convolutional neural network (LeNet) critic. The resulting artificially intelligent artist, whimsically named Hercule LeNet, aims to produce images of low algorithmic complexity which nevertheless resemble a set of real photographs well enough to fool an adversarially trained deep learning critic modeled on the human visual system. Although it is not exposed to any pre-existing art, or asked to mimic the style of any human artist, nevertheless it discovers for itself many of the stylistic features associated with influential art movements of the 19th and 20th Century. A detailed analysis of its work can help us to better understand the way an artist plays with the human visual system to produce aesthetically appealing images.

Keywords

Evolutionary art ai-generated art Artist-critic coevolution Adversarial training Computational creativity 

Notes

Acknowledgment

Thanks to Jacob Soderlund, Darwin Vickers and Tanakrit Udomchoksakul for contributing code, and to Jeff Clune, Ken Stanley, Yoshua Bengio, Oliver Bown and Gary Greenfield for fruitful discussions. This research was undertaken with the support of Akin.com, as well as resources from the National Computational Infrastructure (NCI), which is supported by the Australian Government.

References

  1. 1.
    Galanter, P.: Computational aesthetic evaluation: past and future. In: McCormack, P., d’Inverno, M. (eds.) Computers and Creativity. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-31727-9_10CrossRefGoogle Scholar
  2. 2.
    McCormack, J., Bown, O., Dorin, A., McCabe, J., Monro, G., Whitelaw, M.: Ten questions concerning generative computer art. Leonardo 47(2), 135–141 (2014)CrossRefGoogle Scholar
  3. 3.
    Dawkins, R.: The Blind Watchmaker: Why the Evidence of Evolution Reveals a World Without Design. Norton, New York (1986)Google Scholar
  4. 4.
    Sims, K.: Artificial evolution for computer graphics. ACM Comput. Graph. 25(4), 319–328 (1991)CrossRefGoogle Scholar
  5. 5.
    Kowaliw, T., Dorin, A., McCormack, J.: Promoting creative design in interactive evolutionary computation. IEEE Trans. Evol. Comput. 16(4), 523–536 (2012)CrossRefGoogle Scholar
  6. 6.
    Secretan, J., et al.: Picbreeder: a case study in collaborative evolutionary exploration of design space. Evol. Comput. 19(3), 373–403 (2011)CrossRefGoogle Scholar
  7. 7.
    Machado, P., Correia, J., Romero, J.: Expression-based evolution of faces. In: Machado, P., Romero, J., Carballal, A. (eds.) EvoMUSART 2012. LNCS, vol. 7247, pp. 187–198. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-29142-5_17CrossRefGoogle Scholar
  8. 8.
    Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 427–436 (2015)Google Scholar
  9. 9.
    Baluja, S., Pomerlau, D., Todd, J.: Towards automated artificial evolution for computer-generated images. Connection Sci. 6(2), 325–354 (1994)CrossRefGoogle Scholar
  10. 10.
    Ekárt, A., Sharma, D., Chalakov, S.: Modelling human preference in evolutionary art. In: Di Chio, C., et al. (eds.) EvoApplications 2011. LNCS, vol. 6625, pp. 303–312. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-20520-0_31CrossRefGoogle Scholar
  11. 11.
    Correia, J., Machado, P., Romero, J., Carballal, A.: Feature selection and novelty in computational aesthetics. In: Machado, P., McDermott, J., Carballal, A. (eds.) EvoMUSART 2013. LNCS, vol. 7834, pp. 133–144. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-36955-1_12CrossRefGoogle Scholar
  12. 12.
    Saunders, R., Gero, J.S.: Artificial creativity: a synthetic approach to the study of creative behaviour. In: Computational and Cognitive Models of Creative Design V, pp. 113–139. Key Centre of Design Computing and Cognition, University of Sydney (2001)Google Scholar
  13. 13.
    Machado, P., Romero, J., Manaris, B.: Experiments in computational aesthetics: an iterative approach to stylistic change in evolutionary art. In: Romero, J., Machado, P. (eds.) The Art of Artificial Evolution. Natural Computing Series, pp. 318–415. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-72877-1_18CrossRefGoogle Scholar
  14. 14.
    Greenfield, G., Machado, P.: Simulating artist and critic dynamics – an agent-based application of an evolutionary art system. In: Proceedings of the International Joint Conference on Computational Intelligence (IJCCI), Funchal, Madeira, Portugal, pp. 190–197 (2009)Google Scholar
  15. 15.
    Li, Y., Hu, C.-J.: Aesthetic learning in an interactive evolutionary art system. In: Di Chio, C., et al. (eds.) EvoApplications 2010. LNCS, vol. 6025, pp. 301–310. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-12242-2_31CrossRefGoogle Scholar
  16. 16.
    Correia, J., Machado, P., Romero, J., Carballal, A.: Evolving figurative images using expression-based evolutionary art. In: 4th International Conference on Computational Creativity (ICCC), pp. 24–31 (2013)Google Scholar
  17. 17.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  18. 18.
    Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., Yosinski, J.: Plug & play generative networks: conditional iterative generation of images in latent space. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3510–3520 (2017)Google Scholar
  19. 19.
    Soderlund, J., Blair, A.: Adversarial image generation using evolution and deep learning. In: IEEE Congress on Evolutionary Computation (2018)Google Scholar
  20. 20.
    Blair, A.: Learning the Caesar and Vigenere Cipher by hierarchical evolutionary re-combination. In: IEEE Congress on Evolutionary Computation, pp. 605–612 (2013)Google Scholar
  21. 21.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2323 (1998)CrossRefGoogle Scholar
  22. 22.
    Rooke, S.: Eons of genetically evolved algorithmic images. In: Bentley, P.J., Corne, D.W. (eds.) Creative Evolutionary Systems, pp. 339–365. Morgan Kauffmann, San Francisco (2002)CrossRefGoogle Scholar
  23. 23.
    Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR), pp. 1–15 (2015)Google Scholar
  24. 24.
    Blair, A.D.: Transgenic evolution for classification tasks with HERCL. In: Chalup, S.K., Blair, A.D., Randall, M. (eds.) ACALCI 2015. LNCS (LNAI), vol. 8955, pp. 185–195. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-14803-8_15CrossRefGoogle Scholar
  25. 25.
    Blair, A.: Incremental evolution of HERCL programs for robust control. In: Genetic and Evolutionary Computation Conference (GECCO) Companion, pp. 27–28 (2014)Google Scholar
  26. 26.
    Soderlund, J., Vickers, D., Blair, A.: Parallel hierarchical evolution of string library functions. In: Handl, J., Hart, E., Lewis, P.R., López-Ibáñez, M., Ochoa, G., Paechter, B. (eds.) PPSN 2016. LNCS, vol. 9921, pp. 281–291. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-45823-6_26CrossRefGoogle Scholar
  27. 27.
    Vickers, D., Soderlund, J., Blair, A.: Co-evolving line drawings with hierarchical evolution. In: Wagner, M., Li, X., Hendtlass, T. (eds.) ACALCI 2017. LNCS (LNAI), vol. 10142, pp. 39–49. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-51691-2_4CrossRefGoogle Scholar
  28. 28.
    Krizhevsky, A.: Learning multiple layers of features from tiny images. Master’s Thesis, Computer Science, University of Toronto (2009)Google Scholar
  29. 29.
    Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  30. 30.
    Barnsley, M.: Fractal Image Compression. AK Peters, Natick (1993)zbMATHGoogle Scholar
  31. 31.
    Schmidhuber, J.: Low-complexity art. Leonardo 30(2), 97–103 (1997)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringUniversity of New South WalesSydneyAustralia

Personalised recommendations