braindecode.functional.exact_derivation#
- braindecode.functional.exact_derivation(target, inputs, atol=1e-09)[source]#
WwithW @ xthetargetchannels, from theinputsx.A target is exact when its row of
derivation_matrix()is a combination of the input rows:F3-C3fromC3-F3(weight-1),F3-P3fromF3-C3andC3-P3,F3-C3fromF3andC3. This islinear_channel_map()with every potential unknown, soWis the minimum-norm solution and duplicate measurements are averaged. No reference is guessed:F3-C3is not exact fromF3-R1andC3-R2, andF3is not exact from bipolar channels alone.- Parameters:
target (
list[str]) – Channel names, as inderivation_matrix().inputs (
list[str]) – Channel names, as inderivation_matrix().atol (
float) – Largest residual of an exact row.
- Return type:
- Returns:
weight (torch.Tensor) –
(len(target), len(inputs)), float64; rows of non-exact targets are 0.exact (torch.Tensor) –
(len(target),)bool.