The stepwise activation function works like this – if the sum value is higher than a particular threshold value, we consider the neuron activated. Otherwise, we say that the neuron is inactive.
A graph of this function can be seen in the following diagram:
The function returns 1 (the neuron has been activated) when the argument is > 0 (the zero value is a threshold), and the function returns 0 (the neuron hasn't been activated) otherwise. This approach is easy, but it has flaws. Imagine that we are creating a binary classifier – a model that should say yes or no (activated or not). A stepwise function can do ...
