Learning decay in new Deep Learning (Beta Module)

marvinmc17

Hi everyone,

I am experimenting with the new Deep Learning Module from rapidminer (NOT the Keras module). I was wondering if there is a way how to set

the learning rate decay? I cant find this option anywhere.

sgenzer

cc @pschlunder

pschlunder

Hi marvinmc17,

sorry for the late reply. Some optimizers already have some decay handling build in, RMSProp has the advanced parameter RMSdecay but yes in general it's often helpful to set the decay strategy manually. This isn't available, yet but on the agenda.

Regards,

Philipp