Week 2 > why do we need activation layer > video at 4.29 time duration

Course Q&A Machine Learning Specialization Advanced Learning Algorithms
1

WHAT DOES THESE LINES DESCRIBE
So this big neural network doesn’t do anything

that you can’t also do with logistic regression.

That’s why a common rule of thumb is don’t use

the linear activation function

in the hidden layers of the neural network

image
image1069×526 106 KB

2

Hello @MOHIT_KOTA,

Please check this discussion out.