Neural network for modeling esthetic selection

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Gedeon, T.D.: Neural network for modeling esthetic selection. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds.) ICONIP 2007, Part II. LNCS (LNAI, LNBI), vol. 4985, pp. 666–674. Springer, Heidelberg (2008)



Some real world problems require significant human interaction for labeling the data, which is very expensive. Worse, in some cases, the exercise of human judgement is inherently subjective and contextual, and so the entire labeling must be done in one session, which may be too long. Our domain is the automatic generation of Mondrian-like images with an interactive interface for the user to select images. We use back-propagation neural networks to learn an approximation of a viewer’s aesthetic using 2 category labelled data (images liked/disliked). We construct a data set for training in a sequential fashion related to the interactive art appreciation task, and produce an output profile which well approximates a regression task, even trained on classification data. Analysis of the learned network produces some surprises, with the discovery of some input contributions which are unexpected to the user.

Extended Abstract


Used References

Wikipedia, entries on de stijl, Piet Mondrian,

Hill, A.: Art and Mathesis: Mondrian’s Structures. Leonardo I, 233–234 (1968)

Reynolds, D.: Symbolist Aesthetics And Early Abstract Art, Cambridge UP, page 260 (1995)

McManus, I.C., Cheema, B., Stoker, J.: The aesthetics of composition: A study of Mondrian. Empirical Studies of the Arts 11(2), 83–94 (1993)

Wolach, A.H.: Line spacing in Mondrian paintings and computer-generated modifications. Journal of General Psychology (July 2005)

Gedeon, T.D., Shen, J.Y.: Making art using evolutionary algorithms and artificial AI. In: Proceedings BOOM 2007, p. 6 (2007)

Taylor, R.P.: Fractal expressionism-where art meets science, Art and Complexity. Elsevier Press, Amsterdam (2003)

Gedeon, T.D.: Data Mining of Inputs: Analysing Magnitude and Functional Measures. International Journal of Neural Systems 8(2), 209–218 (1997)

Brown, W.M., Gedeon, T.D., Groves, D.I.: Use of noise to augment training data to compensate for lack of deposit examples in training a neural network for mineral potential mapping. Natural Resources Research 12(2), 141–151 (2003)

Granger, M.J., Mazlack, L.J.: Representing Aesthetic Judgments. In: Proceedings of the International Conference on Cybernetics and Society, pp. 16–20 (1981)

Maiocchi, R.: Can you make a computer understand and produce art? AI & Society 5, 183–201 (1991)


Full Text

[extern file]

intern file

Sonstige Links