We are pleased to announce a collaborative project with Hephaestus Analytical, a company developing cutting-edge machine learning algorithms to solve complex art identification problems. The core of this research is a suite of algorithms that can identify the characteristic patterns that make artists unique. By combining statistical techniques with connoisseurship, they intend to develop scientific language to describe the works of avant-garde artists such as Kazimir Malevich, El Lissitzky and Oleksandr Bohomazov.
Machine learning algorithms are able to detect patterns that our naked eyes cannot. For example, the average pressure with which an artist applies paint when producing broad or precise strokes, or the expected distances between compositional elements. The goal of this cooperative research project is to find out what we might learn about the works of avant-garde artists if machine learning were applied to their works.
To facilitate the project, AARP and Hephaestus are working closely with major public collections at the Stedelijk Museum (Amsterdam), Ludwig Museum (Cologne), Thyssen-Bornemisza Museum (Madrid), National Art Museum of Ukraine (Kyiv), as well as a number of private collectors, to collect data on bonafide, fully-authenticated paintings. These data points will form the backbone for the development of machine learning algorithms for use in the research of the avant-garde.
Collaborative project with Hephaestus Analytical
