Non linearity helps in training your model at a much faster rate and with more accuracy without the loss of your important information
Activation Functions >>> Non linearity helps in training your model at a much faster rate and with more accuracy without the loss of your important information >>> Introduction to TensorFlow
1.
Question 1
Non-linearity helps in training your model at a much faster rate and with more accuracy without the loss of your important information?
1 / 1 point
False
=========================================
3.
Question 3
During the training process, each additional layer in your network can successively reduce signal vs. noise. How can we fix this?
1 / 1 point
Use non-saturating, linear activation functions.
Use non-saturating, nonlinear activation functions such as ReLUs.
Sigmoid or tanh activation functions.
None of the above
=========================================
5.
Question 5
How can we stop ReLU layers from dying?
1 / 1 point
Smaller batch sizes
Batch normalization
Weight regularization
Lower your learning rates
=========================================
2.
Question 2
The activation function which is linear in the positive domain and the function is 0 in the negative domain?
1 / 1 point
A: Sigmoid
Tan-h
ReLU
None of the above.
=========================================
4.
Question 4
How can we solve the problem called internal covariate shift?