A classification method for classifying neural signals, the method comprising the following steps:

  • using a plurality of electrodes over a determined period of time to acquire a plurality of neural signal samples;
  • estimating a covariance matrix of said neural signals; and
  • classifying said neural signals, the classification being performed: either in the Riemann manifold of symmetric positive definite matrices of dimensions equal to the dimensions of said covariance matrix; or else in a tangent space of said Riemann manifold.

A method of selecting neural signal acquisition electrodes based on the Riemann geometry of covariance matrices of said signals. An application of said classification method and of said method of selecting electrodes to direct neural control.