Input data size [72,966500] = 72 channels, 966500 frames
Finding 72 ICA components using extended ICA.
Kurtosis will be calculated initially every 1 blocks using 6000 data points.
Decomposing 186 frames per ICA weight ((5184)^2 = 966500 weights, Initial learning rate will be 0.001, block size 69.
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: -1.39905 to 1.84827
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.
step 1 - lrate 0.000018, wchange 2034280543423787.75000000, angledelta  0.0 deg
Lowering learning rate to 1.31386e-05 and starting again.
step 1 - lrate 0.000013, wchange 105807117944.46995544, angledelta  0.0 deg
Lowering learning rate to 9.45977e-06 and starting again.
step 1 - lrate 0.000009, wchange 86809332.87438254, angledelta  0.0 deg
step 2 - lrate 0.000009, wchange 7494235308012274.00000000, angledelta  0.0 deg
Lowering learning rate to 6.81103e-06 and starting again.
step 1 - lrate 0.000007, wchange 519007.97735304, angledelta  0.0 deg
step 2 - lrate 0.000007, wchange 270090033633.53689575, angledelta  0.0 deg
step 3 - lrate 0.000005, wchange 9950565486129318.00000000, angledelta  0.5 deg
Lowering learning rate to 3.92315e-06 and starting again.
step 1 - lrate 0.000004, wchange 1901.84483201, angledelta  0.0 deg
step 2 - lrate 0.000004, wchange 3681890.87161978, angledelta  0.0 deg
step 3 - lrate 0.000004, wchange 7228037203.85100365, angledelta  6.8 deg
step 4 - lrate 0.000003, wchange 2953904774727.23291016, angledelta  6.8 deg
step 5 - lrate 0.000003, wchange 347026937306396.00000000, angledelta  6.8 deg
step 6 - lrate 0.000002, wchange 14593906516582032.00000000, angledelta  6.8 deg
Lowering learning rate to 1.44623e-06 and starting again.
step 1 - lrate 0.000001, wchange 34.39103353, angledelta  0.0 deg
step 2 - lrate 0.000001, wchange 151.87547714, angledelta  0.0 deg
step 3 - lrate 0.000001, wchange 2485.69349413, angledelta 58.7 deg
step 4 - lrate 0.000001, wchange 40687.73186386, angledelta 58.7 deg
step 5 - lrate 0.000001, wchange 666008.89831454, angledelta 58.7 deg
step 6 - lrate 0.000001, wchange 10901760.12727971, angledelta 58.7 deg
step 7 - lrate 0.000001, wchange 178448632.82575795, angledelta 58.7 deg
step 8 - lrate 0.000001, wchange 2920988428.99386692, angledelta 58.7 deg
step 9 - lrate 0.000001, wchange 21854513124.65024185, angledelta 58.7 deg
step 10 - lrate 0.000001, wchange 100882077871.01475525, angledelta 58.7 deg
step 11 - lrate 0.000001, wchange 315481542046.34857178, angledelta 58.7 deg
step 12 - lrate 0.000001, wchange 721048095274.37744141, angledelta 58.7 deg
step 13 - lrate 0.000000, wchange 1280681969775.14355469, angledelta 58.7 deg
step 14 - lrate 0.000000, wchange 1857510131607.36718750, angledelta 58.7 deg
step 15 - lrate 0.000000, wchange 2289746629969.34619141, angledelta 58.7 deg
step 16 - lrate 0.000000, wchange 2477302245940.93945312, angledelta 58.7 deg
step 17 - lrate 0.000000, wchange 2414004218530.60107422, angledelta 58.7 deg
step 18 - lrate 0.000000, wchange 2163152243681.35791016, angledelta 58.7 deg
step 19 - lrate 0.000000, wchange 1812456526307.33081055, angledelta 58.7 deg
step 20 - lrate 0.000000, wchange 1439090830758.63574219, angledelta 58.7 deg
step 21 - lrate 0.000000, wchange 1094475161192.29907227, angledelta 58.7 deg
step 22 - lrate 0.000000, wchange 804174711245.99194336, angledelta 58.7 deg
step 23 - lrate 0.000000, wchange 574793667839.61193848, angledelta 58.7 deg