Question: Question 4 ( 0 . 6 points ) A good initialization of weights should result in q , Symmetric learning of the weights Constant variance
Question points
A good initialization of weights should result in
Symmetric learning of the weights
Constant variance of activations across the layers
All weight values shrunk towards zero
Nonzero mean of the activations
Step by Step Solution
There are 3 Steps involved in it
1 Expert Approved Answer
Step: 1 Unlock
Question Has Been Solved by an Expert!
Get step-by-step solutions from verified subject matter experts
Step: 2 Unlock
Step: 3 Unlock
