Article

Computer Science and Artificial Intelligence: "Computational Aesthetics"

Authors:
To read the full-text of this research, you can request a copy directly from the author.

Abstract

Computational aesthetics, a subfield of artificial intelligence (AI) concerned with the computational assessment of beauty in domains of human creative expression such as music, visual art, poetry, and chess problems. Typically, mathematical formulas that represent aesthetic features or principles are used in conjunction with specialized algorithms and statistical techniques to provide numerical aesthetic assessments. Those assessments, ideally, can be shown to correlate well with domain-competent or expert human assessment. That can be useful, for example, when willing human assessors are difficult to find or prohibitively expensive or when there are too many objects to be evaluated. Such technology can be more reliable ... https://www.britannica.com/topic/computational-aesthetics

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

... Good references with regard to the field of computational aesthetics can be found in(Iqbal, 2015) and(Galanter, 2012). ...
Preprint
Full-text available
We introduce a new artificial intelligence (AI) approach or technique termed, the 'Digital Synaptic Neural Substrate' (DSNS). This technique uses selected attributes from objects in various domains (e.g. chess problems, classical music, renowned artworks) and recombines them in such a way as to generate new attributes that can then, in principle, be used to create novel objects of creative value to humans relating to any one of the source domains. This allows some of the burden of creative content generation to be passed from humans to machines. The approach was tested primarily in the domain of chess problem composition. We used the DSNS technique to automatically compose numerous sets of chess problems based on attributes extracted and recombined from chess problems and tournament games by humans, renowned paintings, computer-evolved abstract art, photographs of people, and classical music tracks. The quality of these generated chess problems was then assessed automatically using an existing and experimentally-validated computational chess aesthetics model. They were also assessed by human experts in the domain. The results suggest that attributes collected and recombined from chess and other domains using the DSNS approach can indeed be used to automatically generate chess problems of reasonably high aesthetic quality. In particular, a low quality chess source (i.e. tournament game sequences between weak players) used in combination with actual photographs of people was able to produce three-move chess problems of comparable quality or better to those generated using a high quality chess source (i.e. published compositions by human experts), and more efficiently as well. Why information from a foreign domain can be integrated and functional in this way remains an open question for now. The DSNS approach is, in principle, scalable and applicable to any domain in which objects have attributes that can be represented using real numbers. http://arxiv.org/abs/1507.07058
... Good references with regard to the field of computational aesthetics can be found in(Iqbal, 2015) and(Galanter, 2012). ...
Article
Full-text available
We introduce a new artificial intelligence (AI) approach called, the 'Digital Synaptic Neural Substrate' (DSNS). It uses selected attributes from objects in various domains (e.g. chess problems, classical music, renowned artworks) and recombines them in such a way as to generate new attributes that can then, in principle, be used to create novel objects of creative value to humans relating to any one of the source domains. This allows some of the burden of creative content generation to be passed from humans to machines. The approach was tested in the domain of chess problem composition. We used it to automatically compose numerous sets of chess problems based on attributes extracted and recombined from chess problems and tournament games by humans, renowned paintings, computer-evolved abstract art, photographs of people, and classical music tracks. The quality of these generated chess problems was then assessed automatically using an existing and experimentally-validated computational chess aesthetics model. They were also assessed by human experts in the domain. The results suggest that attributes collected and recombined from chess and other domains using the DSNS approach can indeed be used to automatically generate chess problems of reasonably high aesthetic quality. In particular, a low quality chess source (i.e. tournament game sequences between weak players) used in combination with actual photographs of people was able to produce three-move chess problems of comparable quality or better to those generated using a high quality chess source (i.e. published compositions by human experts), and more efficiently as well. Why information from a foreign domain can be integrated and functional in this way remains an open question for now. The DSNS approach is, in principle, scalable and applicable to any domain in which objects have attributes that can be represented using real numbers.
Chapter
We demonstrate how the Digital Synaptic Neural Substrate (DSNS) approach can be applied in the domain of chess problem composition (an area requiring creativity) using fragments of information from classical music, renowned paintings, photos, chess games and other chess problems. Due to the sheer volume produced by computer, the quality of the compositions is assessed using an existing and experimentally-verified computational chess aesthetics model incorporated into a computer program called Chesthetica. In addition, human expert consultation is also used. The experimental results suggest that higher quality compositions can be generated by combining fragments of information from photographs of people and chess games between weak players. While the reasons for this and our other findings remain open questions for now, directions for further work, perhaps even in different domains, are clear. The experimental setups presented should also prove useful to other researchers (not just in artificial intelligence) hoping to replicate or expand upon the findings.
ResearchGate has not been able to resolve any references for this publication.