Dr Aenne Brielmann - Decoding aesthetic value: Can machines learn beauty?

Decoding aesthetic value: Can machines learn beauty?

Dr Aenne Brielmann
Liverpool Hope University

People spend time, money, and effort only to have an aesthetic experience - beautiful sights, concerts, and many more. Can neuro-psychological research explain why we assign value to aesthetic experiences? And if so, can we use these insights to teach a machine what it means for an experience to be beautiful?

I propose the following psychological and computational explanation for why we value aesthetics: Aesthetic value is a signal that serves the greater goal of maintaining and adapting the states of the cognitive-sensory system in order to process stimuli effectively now and in the future. Two interlinked components generate an object’s aesthetic value:
1) processing fluency – how effectively a stimulus is processed right now;
2) learning – the change in how well one anticipates future stimuli can be processed.
This theory can be realized in the form of a computational model. This model can replicate effects of exposure and familiarity on people’s evaluations of objects. It can also predict liking judgments on a trial-by-trial basis (median r=0.65) and outperforms predictions based on population averages (median r=0.01) in a simple image rating task (N=59).
Based on this example model, I will discuss the general benefits of building such theory-guided computational models. Their strength does not merely lie in predictive accuracy but in the interpretability of their components.

Speaker bio: Aenne Brielmann is a Lecturer at Liverpool Hope University. They studied Psychology at the University of Konstanz and received their PhD from New York University. They spent four years as a postdoctoral scholar in Tübingen, first at the Max-Planck Institute for Biological Cybernetics and later at the Hector Research Institute at the University of Tübingen. Their research tackles the questions of why and how people value sensory experiences like watching movies or listening to music. Currently, their work focuses on using and building algorithms - some might call AI - to model and predict people’s preferences for visual objects. Aenne strives to take an interdisciplinary approach, collaborating with philosophers, mathematicians, computer scientists, and architects. They are a current member of the International Association of Empirical Aesthetics’ board of directors and editor for the journal Empirical Studies of the Arts. When they are not busy with their current projects or teaching, they are trying to figure out how to incorporate their love for heavy music and animated media into their research programme.

This talk is part of the MMB & PANC Speaker Series 2025–26 a collaborative initiative between the MSc programmes in Music, Mind and Brain (MMB) and Psychology of Aesthetics, Neuroscience and Creativity (PANC). Full details of the 2025-26 speaker series: https://www.musicmindbrain.com/news-and-events/mmb-panc-speaker-series

Please join us in person if you can. Or click here to join the lecture on Teams.

Dates & times

Accessibility

If you are attending an event and need the College to help with any mobility requirements you may have, please contact the event organiser in advance to ensure we can accommodate your needs.