Department of Electrical Engineering, Stanford University, Stanford, CA 94305-9505, USA.
J Neural Eng. 2012 Apr;9(2):026027. doi: 10.1088/1741-2560/9/2/026027. Epub 2012 Mar 19.
Recurrent neural networks (RNNs) are useful tools for learning nonlinear relationships in time series data with complex temporal dependences. In this paper, we explore the ability of a simplified type of RNN, one with limited modifications to the internal weights called an echostate network (ESN), to effectively and continuously decode monkey reaches during a standard center-out reach task using a cortical brain-machine interface (BMI) in a closed loop. We demonstrate that the RNN, an ESN implementation termed a FORCE decoder (from first order reduced and controlled error learning), learns the task quickly and significantly outperforms the current state-of-the-art method, the velocity Kalman filter (VKF), using the measure of target acquire time. We also demonstrate that the FORCE decoder generalizes to a more difficult task by successfully operating the BMI in a randomized point-to-point task. The FORCE decoder is also robust as measured by the success rate over extended sessions. Finally, we show that decoded cursor dynamics are more like naturalistic hand movements than those of the VKF. Taken together, these results suggest that RNNs in general, and the FORCE decoder in particular, are powerful tools for BMI decoder applications.
递归神经网络 (RNN) 是学习具有复杂时间依赖性的时间序列数据中的非线性关系的有用工具。在本文中，我们探讨了一种简化类型的 RNN 的能力，该 RNN 对内部权重进行了有限的修改，称为回声状态网络 (ESN)，它可以使用皮质脑机接口 (BMI) 在闭环中有效地、连续地解码猴子在标准中心外到达任务中的到达。我们证明，RNN，一种称为 FORCE 解码器的 ESN 实现（来自一阶简化和控制误差学习），快速学习任务，并且在目标获取时间的度量上明显优于当前最先进的方法，即速度卡尔曼滤波器 (VKF)。我们还证明，FORCE 解码器通过在随机点对点任务中成功操作 BMI 来推广到更困难的任务。FORCE 解码器也很稳健，这可以通过扩展会话的成功率来衡量。最后，我们表明解码的光标动态比 VKF 的更像自然的手部运动。总的来说，这些结果表明 RNN 一般来说，特别是 FORCE 解码器，是 BMI 解码器应用的强大工具。
