We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent eb96e76 commit 5134a10Copy full SHA for 5134a10
decode_pattern.m
@@ -10,13 +10,13 @@
10
% .demean Whether the data should be demeaned (per feature,
11
% over trials) prior to decoding. The mean can be
12
% specified in the following ways:
13
-% = 'trainData' The mean of the training data (default).
+% = 'trainData' The nanmean of the training data (default).
14
% = 'testData' The mean of the testing data.
15
% = [F x 1] vector Manually specified mean.
16
% = 'no' No demeaning.
17
% .covariance Whether the pattern should be multiplied by the
18
% inverse of a covariance matrix.
19
-% = 'testData' The covariance of the testing data. Specify
+% = 'testData' The nancov of the testing data. Specify
20
% covariance.gamma for regularization.
21
% = [F x F] vector Manually specified covariance matrix, where F is
22
% the number of features (e.g. sensors).
0 commit comments