This paper was presented at EvoMUSART 2020, which was meant to take place in Sevllle, Spain but due to Coronavirus had to be run completely online. The work is part of an ongoing collaboration between Prof. Jon McCormack at SensiLab and Andy Lomas at Goldsmiths in London.
Abstract: A bottleneck in any evolutionary art system is aesthetic evaluation. Many different methods have been proposed to automate the evaluation of aesthetics, including measures of symmetry, coherence, complexity, contrast and grouping. The interactive genetic algorithm (IGA) relies on human-in-the-loop, subjective evaluation of aesthetics, but limits possibilities for large search due to user fatigue and small population sizes. In this paper we look at how recent advances in deep learning can assist in automating personal aesthetic judgement. Using a leading artist’s computer art dataset, we use dimensionality reduction methods to visualise both geneotype and phenotype space in order to support the exploration of new territory in any generative system. Convolutional Neural Networks trained on the user’s prior aesthetic evaluations are used to suggest new possibilities similar or between known high quality genotype-phenotype mappings.
You can download a preprint on arxiv.
AUTHORS. Jon McCormack, SensiLab, Monash University; Andy Lomas, Dept. of Computing, Goldsmiths, University of London.
WINNER: Best Paper EvoMUSART 2020.