Neural Decoding of Movements: From Linear to Nonlinear Trajectory Models

Authors:
Byron M. Yu;John P. Cunningham;Krishna V. Shenoy;Maneesh Sahani
Affiliations:
Dept. of Electrical Engineering and Neurosciences Program, Stanford University, Stanford, USA and Gatsby Computational Neuroscience Unit, UCL, London, UK;Dept. of Electrical Engineering and Neurosciences Program, Stanford University, Stanford, USA;Dept. of Electrical Engineering and Neurosciences Program, Stanford University, Stanford, USA;Gatsby Computational Neuroscience Unit, UCL, London, UK
Venue:
Neural Information Processing
Year:
2007

Citing 9
Cited 1

On sequential Monte Carlo sampling methods for Bayesian filtering

Statistics and Computing
Expectation Propagation for approximate Bayesian inference

UAI '01 Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence
Information Theory, Inference & Learning Algorithms

Information Theory, Inference & Learning Algorithms
Bayesian Population Decoding of Motor Cortical Activity Using a Kalman Filter

Neural Computation
A State-Space Analysis for Reconstruction of Goal-Directed Movements Using Neural Signals

Neural Computation
Novel approximations for inference in nonlinear dynamical systems using expectation propagation

Neurocomputing
Expectation propagation for approximate inference in dynamic bayesian networks

UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Expectation-propagation for the generative aspect model

UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Gaussian particle filtering

IEEE Transactions on Signal Processing

Sparse Spatio-temporal Gaussian processes with general likelihoods

ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

To date, the neural decoding of time-evolving physical state --- for example, the path of a foraging rat or arm movements --- has been largely carried out using linear trajectory models, primarily due to their computational efficiency. The possibility of better capturing the statistics of the movements using nonlineartrajectory models, thereby yielding more accurate decoded trajectories, is enticing. However, nonlinear decoding usually carries a higher computational cost, which is an important consideration in real-time settings. In this paper, we present techniques for nonlinear decoding employing modal Gaussian approximations, expectatation propagation, and Gaussian quadrature. We compare their decoding accuracy versus computation time tradeoffs based on high-dimensional simulated neural spike counts.