It is said Sigmoid/Tanh are not to use because of the saturation issue.
The saturation occurs when the input to Sigmoid/Tanh is a large value. Will normalizing the input between -1 and 1, for instance using Batch Normalization (BN), avoid the issue?
Please help understand if saturation of sigmoid/tanh is still the issue when such normalization is used.
If the issue is avoided, then is tanh still a valid activation which can avoid the dead ReLU issue?