http://de.evo-art.org/index.php?action=history&feed=atom&title=From_Frank_Lloyd_Wright_to_Mondrian 2026-05-09T22:19:58Z Versionsgeschichte dieser Seite in de_evolutionary_art_org MediaWiki 1.27.4 http://de.evo-art.org/index.php?title=From_Frank_Lloyd_Wright_to_Mondrian&diff=1476&oldid=prev 2014-11-19T14:59:08Z

<p>Die Seite wurde neu angelegt: „ == Reference == Schnier, T., Gero, J.S. (1998). From Frank Lloyd Wright to Mondrian: Transforming evolving representation. In Parmee, I.C., ed.: Adaptive Com…“</p> <p><b>Neue Seite</b></p><div><br /> <br /> == Reference ==<br /> Schnier, T., Gero, J.S. (1998). From Frank Lloyd Wright to Mondrian: Transforming evolving representation. In Parmee, I.C., ed.: Adaptive Computing in Design and Manufacture. Springer. Berlin, 207–219. <br /> <br /> == DOI ==<br /> <br /> == Abstract ==<br /> If a computer is to create designs with the goal of following a certain style, it has to have information about this style.<br /> Unfortunately, the most often used method of formal representations of style, shape grammars, does not lend itself to<br /> automated implementation. However, It has been shown how an evolutionary system with evolving representation can<br /> provide an alternative approach that allows a system to learn style knowledge automatically, and without the need for an<br /> explicit representation.<br /> <br /> This paper shows how the applicability of evolved representation can be extended by the introduction of transforma-<br /> tions of the representation.<br /> <br /> One such transformation allow mixing of style knowledge, similar to the cross-breeding of animals of different races,<br /> with the added possibility of controlling exactly what features are used from which source. This can be achieved by dif-<br /> ferent ways of mixing representations learned from different examples, and then using the new, combined representation<br /> to create new designs. In a similar manner, information learned in one application domain can be used in a different<br /> domain. To achieve this, either the representation or the genotype-phenotype transformation has to be adapted. The same<br /> operations also allow mixing of knowledge from different domains.<br /> <br /> As examples, we show how style information learned from a set of Mondrian paintings can be combined with style<br /> information from a Frank Lloyd Wright window design, to create new window designs. Also, we show how the com-<br /> bined style information can then be used to create three-dimensional objects, showing style features similar to the newly<br /> designed windows.<br /> <br /> == Extended Abstract ==<br /> <br /> == Bibtex == <br /> <br /> == Used References ==<br /> Chan, C.-S. (1995). A cognitive theory of style, Environment and Planning B: Planning and Design 22: 461–47.<br /> <br /> Hanks, D. A. (1989). Frank Lloyd Wright: Preserving an Architectural Heritage, Studio Vista, London.<br /> <br /> Knight, T. (1989). Transformations of De Stijl art: the paintings of Georges Vantongerloo and Fritz Glarner, Environment<br /> and Planning B 16: 51–98.<br /> <br /> Knight, T. W. (1994). Transformations in design: a formal approach to stylistic change and innovation in the visual arts,<br /> Cambridge University Press.<br /> <br /> Schnier, T. &amp; Gero, J. S. (1996). Learning genetic representations as alternative to hand-coded shape grammars, in J. S.<br /> Gero &amp; F. Sudweeks (eds), Artificial Intelligence in Design ’96, Kluwer, Dordrecht, pp. 39–57.<br /> <br /> Schnier, T. &amp; Gero, J. S. (1997). Dominant and recessive genes in evolutionary systems applied to spatial reasoning, Tenth<br /> Australian Joint Conference on Artificial Intelligence. (to be published).<br /> <br /> <br /> == Links ==<br /> === Full Text === <br /> http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.130.7486&amp;rep=rep1&amp;type=pdf<br /> <br /> [[intern file]]<br /> <br /> === Sonstige Links ===<br /> http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.7486</div>

Gbachelier