# How to deal with big output values after classification layer during training?

In AI libraries such as, Tensorflow, Keras etc., how the big output numbers are dealt during training process? For example, for classification layer, it will have some outputs such as [23.4, -21254.3, 32123.4]. In next step, these numbers will go into softmax function which will take power of base e with each output numbers. However, this may result in extreme big numbers in case of extremely large positive number or extremely small negative number. So, how are extreme cases dealt during training process?

• Is this happening even when you have BatchNormalization layer? Feb 9 at 13:46