Rotate your phone to navigate through the site properly

Ludovica Schaerf
Presentation
Critical Visual Theory of the Latent Space

Presentation

Ludovica Schaerf will begin her PhD at the Digital Visual Studies Center between the Max Planck Society (MPG) and the University of Zurich (UZH) in March 2023. She holds a Bachelor’s in Informatics from Amsterdam University College and she recently completed a Master’s of Science in Digital Humanities at the Swiss Federal Institute of Technology of Lausanne (EPFL). Before joining DVS, she worked as a Data Scientist for insurance and academic publishing and as an AI developer in the art market.
Interested in interdisciplinary research between the Arts and Artificial Intelligence, Ludovica has studied, among others, the use of Vision Transformers for Art Authentication compared to the well-established Convolutional Neural Networks; she has investigated the possible effect of using GAN and Diffusion generated synthetic forgeries to aid art authentication and analyze the detectability of AI-generated art. Some of her research spans the field of music and mathematics, analyzing the evolution of Debussy’s music using methods based on the Discrete Fourier Transform.

Critical Visual Theory of the Latent Space

Ludovica’s Ph.D. thesis investigates the nature and nurture of latent spaces, with the aim of formulating a theory of this particular vectorial space. It draws together reflections on the inherent constraints of latent spaces in particular architectures, and considers the learning-specific features that emerge.

The thesis concentrates mostly on the second part, exploring different avenues for understanding the space. Using a multitude of vision generative models, it discusses possibilities for the systematic exploration of the space, including disentanglement properties and coverage of various guidance methods.

It also explores the possibility of mapping across latent spaces, and investigates the differences and commonalities across different learning experiments. Furthermore, the thesis investigates the role of stochasticity in newer models.

As a case study, this thesis adopts art historical data, spanning classic art, photography, and modern and contemporary art.

0,