The Digital Synaptic Neural Substrate: A New Approach to Computational Creativity

We introduce a new artificial intelligence (AI) approach or technique termed, the ‘Digital Synaptic NeuralSubstrate’ (DSNS). This technique uses selected attributes from objects in various domains (e.g. chessproblems, classical music, renowned artworks) and recombines them in such a way as to generate newattributes that can then, in principle, be used to create novel objects of creative value to humans relating toany one of the source domains. This allows some of the burden of creative content generation to be passedfrom 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 attributesextracted 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 thesegenerated chess problems was then assessed automatically using an existing and experimentally-validatedcomputational chess aesthetics model. They were also assessed by human experts in the domain. The resultssuggest that attributes collected and recombined from chess and other domains using the DSNS approach canindeed be used to automatically generate chess problems of reasonably high aesthetic quality. In particular, alow quality chess source (i.e. tournament game sequences between weak players) used in combination withactual photographs of people was able to produce three-move chess problems of comparable quality or betterto those generated using a high quality chess source (i.e. published compositions by human experts), andmore efficiently as well. Why information from a foreign domain can be integrated and functional in this wayremains an open question for now. The DSNS approach is, in principle, scalable and applicable to anydomain in which objects have attributes that can be represented using real numbers.