Empirical Inference Department, Max Planck Institute for Biological Cybernetics, Tübingen, Germany.
J Neural Eng. 2010 Apr;7(2):26003. doi: 10.1088/1741-2560/7/2/026003. Epub 2010 Feb 18.
There is a strong tendency towards discriminative approaches in brain-computer interface (BCI) research. We argue that generative model-based approaches are worth pursuing and propose a simple generative model for the visual ERP-based BCI speller which incorporates prior knowledge about the brain signals. We show that the proposed generative method needs less training data to reach a given letter prediction performance than the state of the art discriminative approaches.
在脑机接口（BCI）研究中存在一种强烈的倾向，即采用判别方法。我们认为基于生成模型的方法值得探索，并为基于视觉 ERP 的 BCI 拼写器提出了一种简单的生成模型，该模型结合了关于脑信号的先验知识。我们表明，与最先进的判别方法相比，所提出的生成方法需要更少的训练数据即可达到给定的字母预测性能。
