Exploring the Exactitudes Portrait Series with Restricted Boltzmann Machines
In this paper we explore the use of deep neural networks to analyze semi-structured series of artworks. We train stacked Restricted Boltzmann Machines on the Exactitudes collection of photo series, and use this to understand the relationship between works and series, uncover underlying features and dimensions, and generate new images. The projection of the series on the two major decorrelated features (PCA on top of Boltzmann features) results in a visualization that clearly reflects the semi structured nature of the photos series, although the original features provide better classification results when assigning photographs to series. This work provides a useful case example of understanding structure that is uncovered by deep neural networks, as well as a tool to analyze the underlying structure of a collection of visual artworks, as a very first step towards a robot curator.
Generated experimental images, including and extending beyond those in this paper, are available for download at high resolution from http://18.104.22.168/evomusart17/.
Sam D. Verkoelen, Maarten H. Lamers, and Peter van der Putten, Exploring the Exactitudes Portrait Series with Restricted Boltzmann Machines. To appear in: Proceedings of the 6th Int Conf on Computational Intelligence in Music, Sound, Art and Design, 2017