期刊
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
卷 14, 期 1, 页码 637-649出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TAFFC.2021.3059043
关键词
Faces; Visualization; Generative adversarial networks; Gallium nitride; Electroencephalography; Psychology; Brain modeling; Brain-computer interfaces; electroencephalography (EEG); generative adversarial networks (GAN); image generation; attraction; personal preferences; individual differences
While it is difficult to explain the exact definition of personal attraction, it depends on implicit processing of complex, culturally and individually defined features. Generative adversarial neural networks (GANs) combined with brain-computer interfaces provide a way to model subjective preferences unconstrained by pre-defined model parameterization. Through an experiment, it was found that using electroencephalography (EEG) to control a GAN produces highly accurate, individually attractive images.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据