1. Brain-Computer Interface for Generating Personally Attractive Images
- Author
-
Keith M. Davis, Lauri Kangassalo, Michiel M. Spapé, Niklas Ravaja, Tuukka Ruotsalo, Zania Sovijärvi-Spape, Department of Psychology and Logopedics, and Department of Computer Science
- Subjects
6162 Cognitive science ,515 Psychology ,generative adversarial networks (GAN) ,050105 experimental psychology ,03 medical and health sciences ,0302 clinical medicine ,Social neuroscience ,Selection (linguistics) ,0501 psychology and cognitive sciences ,electroencephalography (EEG) ,Representation (mathematics) ,individual differences ,Brain–computer interface ,Complex data type ,Artificial neural network ,business.industry ,05 social sciences ,Pattern recognition ,113 Computer and information sciences ,personal preferences ,Visualization ,Human-Computer Interaction ,Face (geometry) ,image generation ,Artificial intelligence ,Brain-computer interfaces ,business ,030217 neurology & neurosurgery ,Software ,attraction - Abstract
While we instantaneously recognize a face as attractive, it is much harder to explain what exactly defines personal attraction. This suggests that attraction depends on implicit processing of complex, culturally and individually defined features. Generative adversarial neural networks (GANs), which learn to mimic complex data distributions, can potentially model subjective preferences unconstrained by pre-defined model parameterization. Here, we present generative brain-computer interfaces (GBCI), coupling GANs with brain-computer interfaces. GBCI first presents a selection of images and captures personalized attractiveness reactions toward the images via electroencephalography. These reactions are then used to control a GAN model, finding a representation that matches the features constituting an attractive image for an individual. We conducted an experiment (N=30) to validate GBCI using a face-generating GAN and producing images that are hypothesized to be individually attractive. In double-blind evaluation of the GBCI-produced images against matched controls, we found GBCI yielded highly accurate results. Thus, the use of EEG responses to control a GAN presents a valid tool for interactive information-generation. Furthermore, the GBCI-derived images visually replicated known effects from social neuroscience, suggesting that the individually responsive, generative nature of GBCI provides a powerful, new tool in mapping individual differences and visualizing cognitive-affective processing.
- Published
- 2023
- Full Text
- View/download PDF