Possible to use different learning rate for different neuron in Keras/Tensorflow?

Question

The simplest example is to have faster/slower learning rates in the upper/lower layers of a network. I found this post on tensorflow.

• Is there a similar trick in Keras?
• Going one step further, can we set different learning rates for specific range/set of neurons/weights in a particular layer?

Answer 1

You can follow this thread here: https://github.com/fchollet/keras/pull/3004 Seems at least that the layer-wise tuning should come.