7. [M21] In Section 5.6.1 the case of all null weights for neurons with the hyperbolic tangent...

Question:

7. [M21] In Section 5.6.1 the case of all null weights for neurons with the hyperbolic tangent has been discussed. It has been proven that both G1 and G2 are null for OHL networks.

However, the gradient with respect to the bias term was not considered. What is its contribution?

Can we extend the stationarity of the gradient to the case of logistic sigmoid?

Fantastic news! We've Found the answer you've been seeking!

Step by Step Answer:

Question Posted: