Convolutional Neural Network¶

Solver ID: CNN

Usage¶

from invert import Solver

# fwd = ...    (mne.Forward object)
# evoked = ... (mne.Evoked object)

solver = Solver("CNN")
solver.make_inverse_operator(fwd)
stc = solver.apply_inverse_operator(evoked)
stc.plot()

Overview¶

Supervised CNN that maps sensor time series to source activity using simulated training data.

References¶

Lukas Hecker 2025, unpublished

API Reference¶

Bases: BaseSolver

Class for the Convolutional Neural Network (CNN) for EEG inverse solutions.

Source code in invert/solvers/neural_networks/cnn.py

class SolverCNN(BaseSolver):  # type: ignore[no-redef]
    """Class for the Convolutional Neural Network (CNN) for EEG inverse solutions."""

    meta = _META

    def __init__(self, name="CNN", **kwargs):
        self.name = name
        self.model = None
        self.optimizer = None
        self.device = None
        return super().__init__(**kwargs)

init ¶

__init__(name='CNN', **kwargs)