As of the latest update, Google Chrome and Microsoft Edge have made a breaking change to how file uploads are handled. Once your system installs this update, you will not be able to upload new images. Please use another browser until we can get it fixed.

Activation function

In neural networks, activation functions perform a transformation on a weighted sum of inputs plus biases to a neuron in order to compute its output. Using a biological analogy, the activation function determines the “firing rate” of a neuron in response to an input or stimulus. These functions introduce non-linearities into the neural networks enabling them to perform complex tasks such as image recognition and language processing. Without non-linear activation functions, artificial neural networks behave as simple linear regression models.

Such functions include:

  • sigmoid function
  • rectified linear unit (ReLU) function
  • hyperbolic tangent (Tanh) function

Artificial intelligence
Share article

Article information

rID: 68974
Synonyms or Alternate Spellings:
  • Activation functions

Support Radiopaedia and see fewer ads

Updating… Please wait.

 Unable to process the form. Check for errors and try again.

 Thank you for updating your details.