crazyfffan's profile - activity

Is there anyway a network can be trained one iteration at a time, printing out some debug (e.g. iteration count, current error) compare current error with max error ,...? Currently I can only blind train a network, not knowing anything happening until the training is done, which is terrible because my current neural network is huge and training should take days or weeks.

I think you have a bug. My Gabor kernel seems normalizes and its values are of (-1, 1), none seems too big nor too small.