Invention Grant
- Patent Title: Iterative calibration method for a direct neural interface using a markov mixture of experts with multivariate regression
-
Application No.: US17011276Application Date: 2020-09-03
-
Publication No.: US12248628B2Publication Date: 2025-03-11
- Inventor: Alexandre Moly , Tetiana Aksenova
- Applicant: COMMISSARIAT A L'ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
- Applicant Address: FR Paris
- Assignee: COMMISSARIAT A L'ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
- Current Assignee: COMMISSARIAT A L'ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
- Current Assignee Address: FR Paris
- Agency: Oblon, McClelland, Maier & Neustadt, L.L.P.
- Priority: FR1909706 20190904
- Main IPC: G06N20/00
- IPC: G06N20/00 ; A61B5/30 ; A61B5/316 ; G06F3/01 ; G06F18/20 ; G06F18/2113 ; G06F18/214 ; G06N7/01 ; G06N20/20
Abstract:
This invention relates to a method of calibrating a direct neural interface with continuous coding. The observation variable is modelled by an HMM model and the control variable is estimated by means of a Markov mixture of experts, each expert being associated with a state of the model.
During each calibration phase, the predictive model of each of the experts is trained on a sub-sequence of observation instants corresponding to the state with which it is associated, using an REW-NPLS (Recursive Exponentially Weighted N-way Partial Least Squares) regression model.
A second predictive model giving the probability of occupancy of each state of the HMM model is also trained during each calibration phase using an REW-NPLS regression method. This second predictive model is used to calculate Markov mixture coefficients during a later operational prediction phase.
During each calibration phase, the predictive model of each of the experts is trained on a sub-sequence of observation instants corresponding to the state with which it is associated, using an REW-NPLS (Recursive Exponentially Weighted N-way Partial Least Squares) regression model.
A second predictive model giving the probability of occupancy of each state of the HMM model is also trained during each calibration phase using an REW-NPLS regression method. This second predictive model is used to calculate Markov mixture coefficients during a later operational prediction phase.
Public/Granted literature
Information query
