Bayesian optimization for automatic design of face stimuli
This work addresses the limitation of using pre-selected stimuli in face processing research by enabling personalized stimuli, which is incremental as it applies existing methods (GANs and Bayesian optimization) to a new domain.
The authors tackled the problem of generating personalized face stimuli for neuroscience and psychology studies by combining GANs with Bayesian optimization to efficiently search latent spaces and maximize individual responses, showing in a web-based study that the algorithm can locate optimal faces and map semantic transformations while revealing individual differences.
Investigating the cognitive and neural mechanisms involved with face processing is a fundamental task in modern neuroscience and psychology. To date, the majority of such studies have focused on the use of pre-selected stimuli. The absence of personalized stimuli presents a serious limitation as it fails to account for how each individual face processing system is tuned to cultural embeddings or how it is disrupted in disease. In this work, we propose a novel framework which combines generative adversarial networks (GANs) with Bayesian optimization to identify individual response patterns to many different faces. Formally, we employ Bayesian optimization to efficiently search the latent space of state-of-the-art GAN models, with the aim to automatically generate novel faces, to maximize an individual subject's response. We present results from a web-based proof-of-principle study, where participants rated images of themselves generated via performing Bayesian optimization over the latent space of a GAN. We show how the algorithm can efficiently locate an individual's optimal face while mapping out their response across different semantic transformations of a face; inter-individual analyses suggest how the approach can provide rich information about individual differences in face processing.