2015-06-23 03:15:22 -0600 | received badge | ● Enthusiast |
2015-06-22 10:43:25 -0600 | commented question | cv::MatEXpr? cameraMatrixLeft where is defined? |
2015-06-21 14:05:57 -0600 | received badge | ● Supporter (source) |
2015-06-21 08:22:37 -0600 | received badge | ● Student (source) |
2015-06-20 08:16:57 -0600 | received badge | ● Editor (source) |
2015-06-18 13:37:50 -0600 | asked a question | Neural Networks UPDATE_WEIGHTS does not work Hi, I'm trying to develop a neural network, where my weights are trained on-line, i.e. training algorithms should be called more times, and each time the net should keep learning starting from the current weights. So I added UPDATE_WEIGHTS flag, but when I use it, prediction and other methods return 0 or nan values. Is there a bug with this flag or am I supposed to do something different? Here the code I used: Since I'd like to create an autoassociator supervision coincides with the pattern features. If, instead, I train my network without using UPDATE_WEIGHTS, I get consistent results. |