Learning in Closed-Loop Brain-Machine Interfaces: Modeling and Experimental Validation
Learning in Closed-Loop Brain-Machine Interfaces: Modeling and Experimental Validation
复制标题
DOI：
10.1109/tsmcb.2009.2036931
复制
发表时间：
2010-10-01
影响因子：
--
通讯作者：
Carmena, Jose M.
中科院分区：
文献类型：
--
作者：
Heliot, Rodolphe;Ganguly, Karunesh;Carmena, Jose M.
脑机接口（BMI）的闭环操作依赖于受试者学习要控制的植物的逆变换的能力。在本文中，我们提出了一个模型的学习过程中，经历闭环BMI操作。我们首先探索的模型的属性，并表明它是能够学习的受控植物的逆模型。然后，我们将模型预测与非人灵长类动物的BMI实际实验神经和行为数据进行比较，这表明模型与实验数据高度一致。将控制理论中的工具应用于这种学习模型将有助于设计新一代神经信息解码器，从而最大限度地提高BMI用户的学习速度。
Closed-loop operation of a brain-machine interface (BMI) relies on the subject's ability to learn an inverse transformation of the plant to be controlled. In this paper, we propose a model of the learning process that undergoes closed-loop BMI operation. We first explore the properties of the model and show that it is able to learn an inverse model of the controlled plant. Then, we compare the model predictions to actual experimental neural and behavioral data from nonhuman primates operating a BMI, which demonstrate high accordance of the model with the experimental data. Applying tools from control theory to this learning model will help in the design of a new generation of neural information decoders which will maximize learning speed for BMI users.