On the Role of Temporary Storage in Interactive Evolution
In typical implementations of interactive evolution of aesthetic material, population size and generation count are limited due to the time-consuming manual evaluation process. We show how a simple device can help to compensate for this, and help to enhance the functionality of interactive evolution. A temporary storage, defined as a number of easily accessed memory locations for evolved objects, adjacent to the evolving population, can be regarded as a non-evolving extension of the population. If sufficiently integrated into the workflow, it provides compensation for limited genetic diversity, an analogy to elitism selection, and means to escape from stagnation of progress through backtracking and reintroduction of previous genomes. If used in a structured way, it can also help the user form a cognitive map of the search space, and use this map to perform a structured, hierarchical exploration. The discussion is based on experiences from a series of implementations of interactive evolution of music and sound, but should be relevant also for other forms of artistic material.
KeywordsInteractive evolution aesthetic selection temporary storage workflow cognitive maps
Unable to display preview. Download preview PDF.
- 1.Dawkins, R.: The Blind Watchmaker. Longman Scientific and Technical, Harlow (1986)Google Scholar
- 2.Sims, K.: Artificial evolution for computer graphics. In: ACM SIGGRAPH 1991 Conference Proceedings, Las Vegas, Nevada, pp. 319–328 (July 1991)Google Scholar
- 3.Biles, J.A.: GenJam: a genetic algorithm for generating jazz solos. In: Proceedings of the International Computer Music Conference, Aarhus, Denmark, pp. 131–137 (1994)Google Scholar
- 5.Dahlstedt, P.: Creating and exploring huge parameter spaces: Interactive evolution as a tool for sound generation. In: Proceedings of the 2001 International Computer Music Conference, Habana, Cuba, pp. 235–242 (2001)Google Scholar
- 7.Dahlstedt, P.: Sounds Unheard of: Evolutionary algorithms as creative tools for the contemporary composer. PhD thesis, Chalmers University of Technology (2004)Google Scholar
- 8.Rooke, S.: Eons of genetically evolved algorithmic images. In: Bentley, P.J., Corne, D.W. (eds.) Creative Evolutionary Systems. Morgan Kaufmann, San Francisco (2001)Google Scholar
- 10.Sáez, Y., Sanjuán, O., Segovia, J., Isasi, P.: Genetic algorithms for the generation of models with micropopulations. In: Cagnoni, S., et al. (eds.) EvoWorkshops 2003. LNCS, vol. 2611, pp. 570–580. Springer, Heidelberg (2003)Google Scholar
- 12.Graf, J., Banzhaf, W.: An expansion operator for interactive evolution. In: Proceedings of IEEE International Conference on Evolutionary Computation, pp. 798–802 (1995)Google Scholar
- 14.Nachmanovitch, S.: Free Play: Improvisation in Life and Art. Jeremy P. Tarcher / Penguin-Putnam Publishing, New York (1990)Google Scholar