Towards automated artificial evolution for computer-generated images

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Baluja, S., Pomerleau, D., Jochem, T.: Towards automated artificial evolution for computer-generated images. Connection Science 6, 325–354 (1994)



In 1991, Karl Sims presented work on artificial evolution in which he used genetic algorithms to evolve complex structures for use in computer-generated images and animations. The evolution of the computer-generated images progressed from simple, randomly generated shapes to interesting images which the users created interactively. The evolution advanced under the constant guidance and supervision of the user. This paper describes attempts to automate the process of image evolution through the use of artificial neural networks. The central objective of this study is to learn the user's preferences, and to apply this knowledge to evolve aesthetically pleasing images which are similar to those evolved through interactive sessions with the user. This paper presents a detailed performance analysis of both the successes and shortcomings encountered in the use of five artificial neural network architectures. Further possibilities for improving the performance of a fully automated system are also discussed.

Extended Abstract


Used References

Baluja, S . (1992) A Massively Bsmlwted Parallel Genetic Algorithm. CMU-CS-92-196R. School of Computer Science, Camegie Mellon University.

Baluja, S . & Pomerleau, D.A. (1994) Non-intrusive gaze tracking using artificial neural networks. In J.D. Cowan, G. Tesauro & J. Alspector (Eds), Advances in Neural Information Processing Systems (NIPS> 6. San Francisco, CA: Morgan Kaufinann.

Baluja, S., Pomerleau, D.A. & Jochem, T. (1993) Simulating a User’s Preferences: Towards Automated Artificial Evolution for Computer Generated Images. CMU-CS-93-198, School of Computer Science, Camegie Mellon University, 1993.

Cohoon, J.P., Hedge, S.U., Martin, W.N. & Richards, D. (1988) Distributed Genetic Algorithmsfor the Floor Plan Design Problem. TR-88-12, School of Engineering and Applied Science, Computer Science Department, University of Virginia.

Goldberg, D.E. (1 989) Generic Algorithms in Search, Optimization, and Machine Learning. Reading, MA. Addison-Wesley.

Hem, J., Krogh, A. & Palmer, R. (1991) Introduction to the Theory of Neural Computation. Reading, MA: Addison-Wesley.

Koza, J.R. (1992) Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge, MA: The MIT Press.

LeCun, Y . , et al. (1989) Backpropagation applied to handwritten zip code recognition. Neural Compu- tation, 1, 54 1-551, Massachusetts Institute of Technology.

Pomerleau, D.A. (1992) hkural Network Perception for Mobile Robot Guidance. PhD Thesis, CMU-CS- 92-1 15. School of Computer Science, Camegie Mellon University.

Sims, K. (1991) Artificial evolution for computer graphics. SIGGRAPH ’91 Conference fioceedings, 2 5 , 319-328.

Todd, P. (1 989) A connectionist approach to algorithmic composition. Compurer Music Journa/, 13, 2743.

Todd, S. & Latham, W. (1992) Evolutionary Art and Computers. Academic Press, London.

Waibel, A. et al. (1989) Phoneme recognition using time-delay neural networks. In A. Waibel & K.F. Lee (Eds), Readings in Speech Recognirion, pp. 393404. San Mateo, CA: Morgan Kaufmann.


Full Text

intern file

Sonstige Links