Brain-Computer Interfaces and Neural Engineering laboratory, School of Computer Science and Electronic Engineering, University of Essex, Essex, United Kingdom.
Department of Otolaryngology | Head and Neck Surgery, Massachusetts Eye and Ear, Boston, MA, United States of America.
J Neural Eng. 2021 May 13;18(4). doi: 10.1088/1741-2552/abf2e4.
In many real-world decision tasks, the information available to the decision maker is incomplete. To account for this uncertainty, we associate a degree of confidence to every decision, representing the likelihood of that decision being correct. In this study, we analyse electroencephalography (EEG) data from 68 participants undertaking eight different perceptual decision-making experiments. Our goals are to investigate (1) whether subject- and task-independent neural correlates of decision confidence exist, and (2) to what degree it is possible to build brain computer interfaces that can estimate confidence on a trial-by-trial basis. The experiments cover a wide range of perceptual tasks, which allowed to separate the task-related, decision-making features from the task-independent ones.Our systems train artificial neural networks to predict the confidence in each decision from EEG data and response times. We compare the decoding performance with three training approaches: (1) single subject, where both training and testing data were acquired from the same person; (2) multi-subject, where all the data pertained to the same task, but the training and testing data came from different users; and (3) multi-task, where the training and testing data came from different tasks and subjects. Finally, we validated our multi-task approach using data from two additional experiments, in which confidence was not reported.We found significant differences in the EEG data for different confidence levels in both stimulus-locked and response-locked epochs. All our approaches were able to predict the confidence between 15% and 35% better than the corresponding reference baselines.Our results suggest that confidence in perceptual decision making tasks could be reconstructed from neural signals even when using transfer learning approaches. These confidence estimates are based on the decision-making process rather than just the confidence-reporting process.
在许多实际决策任务中,决策者可用的信息是不完整的。为了考虑到这种不确定性,我们为每个决策分配一定程度的置信度,代表该决策正确的可能性。在这项研究中,我们分析了 68 名参与者在进行 8 种不同感知决策实验时的脑电图(EEG)数据。我们的目标是研究:(1)是否存在与个体和任务无关的决策置信度的神经相关性;(2)在多大程度上可以构建能够逐试估计置信度的脑机接口。这些实验涵盖了广泛的感知任务,这使得我们能够将与任务相关的决策特征与与任务无关的特征区分开来。我们的系统训练人工神经网络,根据 EEG 数据和反应时间来预测每个决策的置信度。我们比较了三种训练方法的解码性能:(1)单个体,训练和测试数据均来自同一个人;(2)多个体,所有数据都属于同一个任务,但训练和测试数据来自不同的用户;(3)多任务,训练和测试数据来自不同的任务和个体。最后,我们使用来自另外两个未报告置信度的实验的数据验证了我们的多任务方法。我们发现,在刺激锁定和反应锁定时期,不同置信水平的 EEG 数据存在显著差异。我们的所有方法都能够在 15%到 35%之间更好地预测置信度,而相应的参考基线只能预测 10%到 25%。我们的结果表明,即使使用转移学习方法,也可以从神经信号中重建感知决策任务的置信度。这些置信度估计是基于决策过程,而不仅仅是置信度报告过程。