clstm
clstm copied to clipboard
What Gradient Descent Method clstm is using?
What Gradient Descent Method clstm is using? SGD? AdaGrad? NAG? RMSProp? Adam? I want to increase the speed of the learning. If clstm is not using adaptive learning rate algorithm, I also have to ask that this method can change the learning rate dynamically to implement adaptive learning rate algorithm:
net.setLearningRate(1e-4,0.9)
Oh, I found this method in the test-clstm.py. SGD+momenum.
clstm.sgd_update(net)
Is there adagrad, NAG, or faster solver? SGD is quite slow.