Multiplicative recurrent neural network for fast and robust intracortical brain machine interface decoders
A brain machine interface (BMI) to control a device is provided. The BMI has a neural decoder, which is a neural to kinematic mapping function with neural signals as input to the neural decoder and kinematics to control the device as output of the neural decoder. The neural decoder is based on a continuous-time multiplicative recurrent neural network, which has been trained as a neural to kinematic mapping function. An advantage of the invention is the robustness of the decoder to perturbations in the neural data; its performance degrades less—or not at all in some circumstances—in comparison to the current state decoders. These perturbations make the current use of BMI in a clinical setting extremely challenging. This invention helps to ameliorate this problem. The robustness of the neural decoder does not come at the cost of some performance, in fact an improvement in performance is observed.
1. A brain machine interface to control a device, comprising: the brain machine interface having a neural decoder wherein the neural decoder is a continuous-time multiplicative recurrent neural network trained as a neural to kinematic mapping function with neural signals from a brain of a subject as input to the neural decoder and kinematics to control the device as output of the neural decoder, wherein neural training data used for training the neural to kinematic mapping function has been modified by randomly adding and removing spikes such that the mean number of spikes is preserved on average, and wherein the brain machine interface converts the neural signals from motor regions of the brain of the subject into kinematic control signals to control the device.
2. The brain machine interface as set forth in claim 1 , wherein the outputted kinematics is normalized position over time and/or velocity over time.
3. The brain machine interface as set forth in claim 1 , wherein the device to be controlled is a robotic arm, a prosthetic device or a cursor on a computer screen.
4. The brain machine interface as set forth in claim 1 , wherein the neural decoder has been trained with neural and kinematic data sets collected over multiple days.
5. The brain machine interface as set forth in claim 1 , wherein the neural decoder has been trained with neural and kinematic data sets collected over five or more days.