Input data size [72,1088500] = 72 channels, 1088500 frames
Finding 72 ICA components using extended ICA.
Kurtosis will be calculated initially every 1 blocks using 6000 data points.
Decomposing 209 frames per ICA weight ((5184)^2 = 1088500 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: -3.83808 to 3.35865
Computing the sphering matrix...
Starting weights are the identity matrix ...
Sphering the data ...
Beginning ICA training ... first training step may be slow ...
Lowering learning rate to 0.0009 and starting again.
Lowering learning rate to 0.00081 and starting again.
Lowering learning rate to 0.000729 and starting again.
Lowering learning rate to 0.0006561 and starting again.
Lowering learning rate to 0.00059049 and starting again.
Lowering learning rate to 0.000531441 and starting again.
Lowering learning rate to 0.000478297 and starting again.
Lowering learning rate to 0.000430467 and starting again.
Lowering learning rate to 0.00038742 and starting again.
Lowering learning rate to 0.000348678 and starting again.
Lowering learning rate to 0.000313811 and starting again.
Lowering learning rate to 0.00028243 and starting again.
Lowering learning rate to 0.000254187 and starting again.
Lowering learning rate to 0.000228768 and starting again.
Lowering learning rate to 0.000205891 and starting again.
Lowering learning rate to 0.000185302 and starting again.
Lowering learning rate to 0.000166772 and starting again.
Lowering learning rate to 0.000150095 and starting again.
Lowering learning rate to 0.000135085 and starting again.
Lowering learning rate to 0.000121577 and starting again.
Lowering learning rate to 0.000109419 and starting again.
Lowering learning rate to 9.84771e-05 and starting again.
Lowering learning rate to 8.86294e-05 and starting again.
Lowering learning rate to 7.97664e-05 and starting again.
Lowering learning rate to 7.17898e-05 and starting again.
Lowering learning rate to 6.46108e-05 and starting again.
Lowering learning rate to 5.81497e-05 and starting again.
Lowering learning rate to 5.23348e-05 and starting again.
Lowering learning rate to 4.71013e-05 and starting again.
Lowering learning rate to 4.23912e-05 and starting again.
Lowering learning rate to 3.8152e-05 and starting again.
Lowering learning rate to 3.43368e-05 and starting again.
Lowering learning rate to 3.09032e-05 and starting again.
Lowering learning rate to 2.78128e-05 and starting again.
Lowering learning rate to 2.50316e-05 and starting again.
Lowering learning rate to 2.25284e-05 and starting again.
Lowering learning rate to 2.02756e-05 and starting again.
Lowering learning rate to 1.8248e-05 and starting again.
Lowering learning rate to 1.64232e-05 and starting again.
step 1 - lrate 0.000016, wchange 3288973440574485.00000000, angledelta  0.0 deg
Lowering learning rate to 1.18247e-05 and starting again.
step 1 - lrate 0.000012, wchange 149675030552.38568115, angledelta  0.0 deg
Lowering learning rate to 8.51379e-06 and starting again.
step 1 - lrate 0.000009, wchange 111418919.69773673, angledelta  0.0 deg
step 2 - lrate 0.000009, wchange 12259479825851494.00000000, angledelta  0.0 deg
Lowering learning rate to 6.12993e-06 and starting again.
step 1 - lrate 0.000006, wchange 621255.39013165, angledelta  0.0 deg
step 2 - lrate 0.000006, wchange 386904869094.20056152, angledelta  0.0 deg
step 3 - lrate 0.000005, wchange 16319215534816376.00000000, angledelta  0.5 deg
Lowering learning rate to 3.53084e-06 and starting again.
step 1 - lrate 0.000004, wchange 2111.04968859, angledelta  0.0 deg
step 2 - lrate 0.000004, wchange 4538193.98144789, angledelta  0.0 deg
step 3 - lrate 0.000004, wchange 9879474040.31827927, angledelta  6.4 deg
step 4 - lrate 0.000003, wchange 4393325850256.29687500, angledelta  6.4 deg
step 5 - lrate 0.000002, wchange 552442072796003.50000000, angledelta  6.4 deg
step 6 - lrate 0.000002, wchange 24071809351161804.00000000, angledelta  6.4 deg
Lowering learning rate to 1.30161e-06 and starting again.
step 1 - lrate 0.000001, wchange 34.93951030, angledelta  0.0 deg
step 2 - lrate 0.000001, wchange 165.93068591, angledelta  0.0 deg
step 3 - lrate 0.000001, wchange 2821.27125880, angledelta 58.1 deg
step 4 - lrate 0.000001, wchange 47973.96990549, angledelta 58.1 deg
step 5 - lrate 0.000001, wchange 815768.50845094, angledelta 58.1 deg
step 6 - lrate 0.000001, wchange 13871653.69926920, angledelta 58.1 deg
step 7 - lrate 0.000001, wchange 235879143.41917828, angledelta 58.1 deg
step 8 - lrate 0.000001, wchange 4010983194.57209921, angledelta 58.1 deg
step 9 - lrate 0.000001, wchange 31009046222.13662338, angledelta 58.1 deg
step 10 - lrate 0.000001, wchange 146973744419.56405640, angledelta 58.1 deg
step 11 - lrate 0.000001, wchange 469512830795.44805908, angledelta 58.1 deg
step 12 - lrate 0.000001, wchange 1091636185535.40283203, angledelta 58.1 deg
step 13 - lrate 0.000000, wchange 1965769059634.04272461, angledelta 58.1 deg
step 14 - lrate 0.000000, wchange 2882823278860.95849609, angledelta 58.1 deg
step 15 - lrate 0.000000, wchange 3585218237147.19726562, angledelta 58.1 deg
step 16 - lrate 0.000000, wchange 3906422330258.29150391, angledelta 58.1 deg
step 17 - lrate 0.000000, wchange 3828171551403.22119141, angledelta 58.1 deg
step 18 - lrate 0.000000, wchange 3445850420487.08642578, angledelta 58.1 deg
step 19 - lrate 0.000000, wchange 2897585359937.38134766, angledelta 58.1 deg
step 20 - lrate 0.000000, wchange 2307265571308.73046875, angledelta 58.1 deg
step 21 - lrate 0.000000, wchange 1758740847409.06616211, angledelta 58.1 deg
step 22 - lrate 0.000000, wchange 1294595494572.76147461, angledelta 58.1 deg
step 23 - lrate 0.000000, wchange 926662140612.25805664, angledelta 58.1 deg