[eu-gene] need advice on a framework design
list at philipgalanter.com
Wed Jan 25 18:10:48 GMT 2012
David, I get the feeling we are talking past each other. Here is what I'm saying:
(1) to date *I* find evolving expression graphics to be an aesthetic dead end. I feel like I pushed them as far as *I* could in the previous work I posted, I've not seen other work that makes me think otherwise, and so I'm not going to pursue that avenue further.
(2) I find it puzzling that at least two significant researchers in the relatively small field of "automated fitness functions for evolutionary art" have both seized on evolving expression images as their test bed. I question whether any future positive result from their research will have more general relevance. (see cites below)
(3) Just because evolving expressions generates an image via pixel-by-pixel calculations, that doesn't mean it is a good tool for general image making. Perhaps it can be shown in principle that any possible image can be calculated/generated from expressions. But there is no guarantee that there is a practical way to evolve the needed expressions. Thousands of generations prior to the desired result it's not clear which genotype is on the way to getting there.
(4) Evolving expressions are not a good tool for general image making, but that in itself is not a sin. But if the claim is made that evolving expressions *are* a good tool for general image making, I'm unaware of anyway it can be substantiated.
Greenfeld, G. R. (2003). Evolving aesthetic images using multiobjective optimization, CEC: 2003 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-4, PROCEEDINGS pp. 1903–1909.
Greenfield, G. R. (2008b). Co-evolutionary methods in evolutionary art, in J. Romero and P. Machado (eds), The Art Of Artificial Evolution, Natural Computing Series, Springer Berlin Heidelberg, pp. 357–380.
Machado, P. and Cardoso, A. (2002). All the truth about nevar, Applied Intelligence 16(2): 101– 118.
Machado, P., Romero, J. and Manaris, B. (2008). Experiments in computational aesthetics - an iterative approach to stylistic change in evolutionary art, in J. Romero and P. Machado (eds), The art of artificial evolution : a handbook on evolutionary art and music, Springer, Berlin, pp. 311–332.
On Jan 24, 2012, at 11:06 PM, David Hart wrote:
> Well the proof of the pudding will be in the tasting and so as soon as evolving expressions yield a wide variety of personalized graphical styles I'll be happy to concede the obvious.
> I guess the main thing I'm wondering is why you are seemingly holding evolved expressions to a far higher standard than all other generative art? Are there any generative formats or techniques, evolutionary or otherwise, anywhere, that have yielded a wide variety of personalized graphical styles? I've never seen one, nothing that even remotely approaches that bar. Most human traditional artists don't meet that criteria. ;) Maybe because evolutionary theory says it ought to be possible, it is a larger disappointment than other approaches with less lofty goals?
> 'In this forum this kind of thrown egg is likely to land on your own face.'
> To unsubscribe from eu-gene visit
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the eu-gene