Learning in closed-loop brain-machine interfaces: modeling and experimental validation

Authors:
Rodolphe Héliot;Karunesh Ganguly;Jessica Jimenez;Jose M. Carmena
Affiliations:
Department of Electrical Engineering and Computer Sciences and the Helen Wills Neuroscience Institute, University of California, Berkeley, CA;Neurology and Rehabilitation Services, San Francisco VA Medical Center, San Francisco, CA and Dept. of Elect. Eng. and Comp. Sci. and the Helen Wills Neurosci. Inst., Univ. of California, Berkeley ...;Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA;Department of Electrical Engineering and Computer Sciences, Helen Wills Neuroscience Institute, University of California, Berkeley, CA
Venue:
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Year:
2010

Citing 5
Cited 4

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
A Fast Stochastic Error-Descent Algorithm for Supervised Learning and Optimization

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Modeling Sensorimotor Learning with Linear Dynamical Systems

Neural Computation
An implementation of reinforcement learning based on spike timing dependent plasticity

Biological Cybernetics
Learning flexible sensori-motor mappings in a complex network

Biological Cybernetics

Stochastic optimal control as a theory of brain-machine interface operation

Neural Computation
Design and analysis of closed-loop decoder adaptation algorithms for brain-machine interfaces

Neural Computation
Dynamic analysis of naive adaptive brain-machine interfaces

Neural Computation
Dynamic analysis of naive adaptive brain-machine interfaces

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.