Sigmoid function

A sigmoid function is a non-linear mathematical function that exhibits a sigmoid curve, as illustrated in Figure 3.7, and often refers to the sigmoid or logistic function:

In this case, the sigmoid activation function is bounded between 0 and 1 and is smoothly defined for all real input values, making it a better choice of activation function than a basic Heaviside step function. This is because, unlike the Heaviside step function, non-linear activation functions can distinguish data that is not linearly separable, such as image and video data. Note that by using the sigmoid function as the activation function, the artificial ...

Get Machine Learning with Apache Spark Quick Start Guide now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.