Backpropagation (machine learning)

Last revised by Assoc Prof Frank Gaillard on 04 Oct 2020

Backpropagation in supervised machine learning is the process used to calculate the gradient of the error function associated with each parameter weighting within a convoluted neural network (CNN). Essentially, the gradient estimates how the system parameters should change in order to optimize the network overall 1,2.

 

ADVERTISEMENT: Supporters see fewer/no ads

Updating… Please wait.

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

 Thank you for updating your details.