Attempting to convert data matrix to double precision for more accurate ICA results.
Input data size [66,1110360] = 66 channels, 1110360 frames/nFinding 66 ICA components using extended ICA.
Kurtosis will be calculated initially every 1 blocks using 6000 data points.
Decomposing 254 frames per ICA weight ((4356)^2 = 1110360 weights, Initial learning rate will be 0.001, block size 70.
Learning rate will be multiplied by 0.98 whenever angledelta >= 60 deg.
More than 32 channels: default stopping weight change 1E-7
Training will end when wchange < 1e-07 or after 512 steps.
Online bias adjustment will be used.
Removing mean of each channel ...
Final training data range: -2587.29 to 2538.28
Computing the sphering matrix...
Starting weights are the identity matrix ...
Sphering the data ...
Beginning ICA training ... first training step may be slow ...
警告: 使用 'state' 设置 RAND 的内部状态，将导致 RAND、RANDI 和 RANDN 使用旧的随机数生成函数。建议不要使用该语法。请参阅替换不提倡使用的 rand 和 randn 语法，使
用 RNG 来替换旧语法。
In runica (line 830)
In pop_runica (line 399)
Lowering learning rate to 0.0009 and starting again
不知道哪里出错了 求大家帮下忙
