A sigmoid activation function is used in many neural networks. The properties of a sigmoid function mean that it shares some of the non-linearity of a threshold function, but is differentiable enabling learning through the backpropagation algorithm.
Used in Chap. 6: pages 76, 78; Chap. 7: page 99; Chap. 9: page 127; Chap. 21: page 337
Used in glossary entries: neural network, sigmoid function, threshold function
Sigmoid function smoothly limits extreme values