A sigmoid function maps any real-valued input into a bounded range, commonly between 0 and 1. In machine learning, it is often used to convert raw model scores into probabilities or as an activation function in neural networks.
A mathematical function that "squishes" an input value into a constrained range, typically 0 to 1 or -1 to +1. That is, you can pass any number (two, a million, negative billion, whatever) to a sigmoid and the output will still be in the constrained range. A plot of the sigmoid activation function looks as follows: !A two-dimensional curved plot with x values spanning the domain -infinity to +positive, while y values span the range almost 0 to almost 1. When x is 0, y is 0.5. The slope of the curve is always positive, with the highest slope at 0,0.5 and gradually decreasing slopes as the absolute value of x increases. The sigmoid function has several uses in machine learning, including: - Converting the raw output of a logistic regression or multinomial regression model to a probability. - Acting as an activation function in some neural networks. The sigmoid function over an input number x has the following formula: In machine learning, x is generally a weighted sum.