The sigmoid function is defined by the following equation:
It is used in neural networks because it’s differentiable, and this is necessary for back propagation, and its co-domain is , which can be used as probabilities.
The sigmoid function is defined by the following equation:
f(x)=1+e−x1It is used in neural networks because it’s differentiable, and this is necessary for back propagation, and its co-domain is [0,1], which can be used as probabilities.