Derivative of Relu in output layer

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
73

Exactly as @paulinpaloalto’s explained. Therefore, the hint is from you.

leaky relu isn’t that bad, look at my results:

EditSave_2022_12_04_07_41_28
EditSave_2022_12_04_07_41_281659×772 64.8 KB

I have made these changes, have you done the same:

    # dAL = (1./m)*(AL-Y) #commented this
    dAL = AL-Y #uncommented this
  1. change “relu” to “leaky_relu”. There are 4 places to change. 4 places :wink:

That’s nice!

Deep and dark.

Cheers,
Raymond

2 Likes