The sigmoid function is a mathematical function that transforms any real-valued number into a value between 0 and 1. It is commonly used in machine learning, particularly in logistic regression and neural networks, to model probabilities.
Often used as an activation function in a few specific neural net architectures, however not as popular as ReLU these days due to computational efficiency.
Also usefull for anything involving probabilities, since it maps any input to a value between 0 and 1. Not exactly like Softmax, but similar idea.