lstmupdate

Update net parameters via lstm optimizer

NET = LSTMUPDATE(NET,GRAD,ITER)

Updates the learnable parameters of the dlnetwork NET using the Lstm optimizer, the number of hidden units in lstm network is 100, the update of lstm net using the Adam gradient descent algorithm, with a default global learning rate of 0.001, a gradient decay factor of 0.9 and a squared gradient decay factor of 0.999. Use LSTMUPDATE to iteratively update learnable parameters during network training.

original paper