Suppose I have skewed distributions of classes in train set.
How should I deal with it? Just train and network will deal itself? Or some methods are good?
For example, can I artificially make distribution uniform, then train my network and then apply some bayessian methods to take probabilities into account?
Distributions of classes is following:
This is from
Planet: Understanding the Amazon from Space competition on Kaggle. Plot is from this kernel. Multilayered convolutional network is used.