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.
KeywordsFeature Space Deep Learning Deep Neural Network Restrict Boltzmann Machine Pixel Space
We acknowledge Ari Versluis and Ellie Uyttenbroek as the creators of Exactitudes and owners of all intellectual rights and privileges, and are grateful to them for sharing this wonderful collection with the world via www.exactitudes.com.
- 1.Candy, F.J.: The fabric of society: an investigation of the emotional and sensory experience of wearing denim clothing. Sociol. Res. Online 10(1) (2005)Google Scholar
- 2.Casimir, G.: Interaction of societal development and communication technology. Int. J. Home Econ. 4(1), 3–13 (2011)Google Scholar
- 3.DeMers, D., Cottrell, G.: Non-linear dimensionality reduction. Adv. Neural Inf. Process. Syst. 5, 580–587 (1993)Google Scholar
- 4.Doherty, P.C.: The Beginner’s Guide to Winning the Nobel Prize: Advice for Young Scientists. Columbia University Press, New York (2008)Google Scholar
- 5.Gardien, P., Djajadiningrat, T., Hummels, C., Brombacher, A.: Changing your hammer: the implications of paradigmatic innovation for design practice. Int. J. Des. 8(2), 119–139 (2014)Google Scholar
- 6.Arntzen, M.G.: Dress Code: The Naked Truth About Fashion. Reaktion Books (2015)Google Scholar
- 9.Huffington Post. Artists Create Anthropological Photo Series (2012). www.huffingtonpost.com/2012/06/25/exactitudes-interview-art_n_1619483.html. Retrieved on: 10 Nov 2016
- 10.Ranzato, M.A., Poultney, C., Chopra, S., LeCun, Y.: Efficient learning of sparse representations with an energy-based model. In: Advances in Neural Information Processing Systems, vol. 19, pp. 1137–1144 (2006)Google Scholar
- 11.Smelik, A.: The performance of authenticity. ADDRESS J. Fashion Writ. Criticism 1(1), 76–82 (2011)Google Scholar
- 12.Trocchianesi, R., Guglielmetti, I.: Design teaching and cultural companies: Languages, tools and methods toward a profitable involvement. Strateg. Des. Res. J. 5(1), 49–57 (2012)Google Scholar
- 13.Verkoelen, S.D.: Exploring Dimensionality Reduction on Semi-structured Photos — A Closer Look at Exactitudes. Master’s Thesis for the Media Technology programme, Leiden University (The Netherlands) (2015)Google Scholar
- 14.Versluis, A., Uyttenbroek, E.: Exactitudes. 010 Publishers, Rotterdam (2002)Google Scholar